Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3345 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1731851 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3810. Min Act: -0.0000

Data Index: 246229 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3582. Min Act: -0.0000

Data Index: 614284 (The Pile)

Max Activating Token Index: 443

Text #3

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1614194 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3392. Min Act: -0.0000

Data Index: 637284 (The Pile)

Max Activating Token Index: 581

Text #5

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1175642 (The Pile)

Max Activating Token Index: 786

Text #6

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3375. Min Act: -0.0000

Data Index: 480313 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3499. Min Act: -0.0000

Data Index: 1564301 (The Pile)

Max Activating Token Index: 204

Text #8

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3495. Min Act: -0.0000

Data Index: 471388 (The Pile)

Max Activating Token Index: 823

Text #9

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3295. Min Act: 0.0000

Data Index: 1326879 (The Pile)

Max Activating Token Index: 101

Text #10

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3418. Min Act: 0.0000

Data Index: 120517 (The Pile)

Max Activating Token Index: 897

Text #11

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3522. Min Act: -0.0000

Data Index: 1036290 (The Pile)

Max Activating Token Index: 870

Text #12

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1564691 (The Pile)

Max Activating Token Index: 752

Text #13

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1351771 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1153196 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3266. Min Act: -0.0000

Data Index: 3340 (The Pile)

Max Activating Token Index: 548

Text #16

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3246. Min Act: -0.0000

Data Index: 499252 (The Pile)

Max Activating Token Index: 1008

Text #17

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3234. Min Act: -0.0000

Data Index: 201885 (The Pile)

Max Activating Token Index: 777

Text #18

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3214. Min Act: -0.0000

Data Index: 477233 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3198. Min Act: -0.0000

Data Index: 178673 (The Pile)

Max Activating Token Index: 791