< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2369 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.7439. Min Act: -0.0002

Data Index: 1584189 (The Pile)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6084. Min Act: -0.0002

Data Index: 173258 (The Pile)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6009. Min Act: -0.0002

Data Index: 134531 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5743. Min Act: -0.0002

Data Index: 1390691 (The Pile)

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5727. Min Act: -0.0002

Data Index: 429826 (The Pile)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5582. Min Act: -0.0002

Data Index: 1319558 (The Pile)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5020. Min Act: -0.0002

Data Index: 103547 (The Pile)

Max Activating Token Index: 717

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5149. Min Act: -0.0002

Data Index: 119528 (The Pile)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5106. Min Act: -0.0002

Data Index: 940960 (The Pile)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5160. Min Act: -0.0002

Data Index: 370233 (The Pile)

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5321. Min Act: -0.0002

Data Index: 417224 (The Pile)

Max Activating Token Index: 194

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5275. Min Act: -0.0002

Data Index: 1311104 (The Pile)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5239. Min Act: -0.0002

Data Index: 1973205 (The Pile)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5018. Min Act: -0.0002

Data Index: 792229 (The Pile)

Max Activating Token Index: 216

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5217. Min Act: -0.0002

Data Index: 948746 (The Pile)

Max Activating Token Index: 853

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5381. Min Act: -0.0002

Data Index: 850798 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5079. Min Act: -0.0002

Data Index: 749685 (The Pile)

Max Activating Token Index: 702

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4983. Min Act: -0.0002

Data Index: 710799 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5034. Min Act: -0.0002

Data Index: 462069 (The Pile)

Max Activating Token Index: 331

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5144. Min Act: -0.0002

Data Index: 1573949 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #19