Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3550 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.7157. Min Act: -0.0000

Data Index: 1999402 (The Pile)

Max Activating Token Index: 333

Text #1

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.7512. Min Act: -0.0000

Data Index: 1748129 (The Pile)

Max Activating Token Index: 869

Text #2

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.0682. Min Act: -0.0000

Data Index: 605046 (The Pile)

Max Activating Token Index: 892

Text #3

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.0440. Min Act: -0.0000

Data Index: 573362 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.7096. Min Act: -0.0000

Data Index: 630105 (The Pile)

Max Activating Token Index: 954

Text #5

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.7095. Min Act: -0.0000

Data Index: 446539 (The Pile)

Max Activating Token Index: 632

Text #6

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.7203. Min Act: -0.0000

Data Index: 1767991 (The Pile)

Max Activating Token Index: 525

Text #7

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.6781. Min Act: -0.0000

Data Index: 1604349 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.4800. Min Act: -0.0000

Data Index: 1584280 (The Pile)

Max Activating Token Index: 618

Text #9

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.4808. Min Act: -0.0000

Data Index: 241153 (The Pile)

Max Activating Token Index: 592

Text #10

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.4467. Min Act: -0.0000

Data Index: 1949012 (The Pile)

Max Activating Token Index: 316

Text #11

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.4311. Min Act: -0.0000

Data Index: 119489 (The Pile)

Max Activating Token Index: 150

Text #12

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.4348. Min Act: -0.0000

Data Index: 1245749 (The Pile)

Max Activating Token Index: 466

Text #13

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.7382. Min Act: -0.0000

Data Index: 1705025 (The Pile)

Max Activating Token Index: 525

Text #14

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.7204. Min Act: -0.0000

Data Index: 1076592 (The Pile)

Max Activating Token Index: 642

Text #15

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.1557. Min Act: -0.0000

Data Index: 343997 (The Pile)

Max Activating Token Index: 886

Text #16

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.3098. Min Act: -0.0000

Data Index: 1139978 (The Pile)

Max Activating Token Index: 163

Text #17

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.3015. Min Act: -0.0000

Data Index: 710755 (The Pile)

Max Activating Token Index: 830

Text #18

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.3064. Min Act: -0.0000

Data Index: 505784 (The Pile)

Max Activating Token Index: 609

Text #19

Max Range: 5.7512. Min Range: -5.7512

Max Act: 4.1450. Min Act: -0.0000

Data Index: 1080305 (The Pile)

Max Activating Token Index: 387