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

Dataset: The Pile

Neuron 67 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.5222. Min Act: -0.0000

Data Index: 1204297 (The Pile)

Max Activating Token Index: 189

Text #1

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.3986. Min Act: -0.0000

Data Index: 1830235 (The Pile)

Max Activating Token Index: 631

Text #2

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.3221. Min Act: -0.0000

Data Index: 1031225 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.4144. Min Act: -0.0000

Data Index: 939725 (The Pile)

Max Activating Token Index: 706

Text #4

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.9322. Min Act: -0.0000

Data Index: 1800229 (The Pile)

Max Activating Token Index: 567

Text #5

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.0059. Min Act: -0.0000

Data Index: 301723 (The Pile)

Max Activating Token Index: 740

Text #6

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.8296. Min Act: -0.0000

Data Index: 766120 (The Pile)

Max Activating Token Index: 541

Text #7

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.1262. Min Act: -0.0000

Data Index: 51818 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.7639. Min Act: -0.0000

Data Index: 471213 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.6177. Min Act: -0.0000

Data Index: 600808 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.8172. Min Act: -0.0000

Data Index: 1322435 (The Pile)

Max Activating Token Index: 85

Text #11

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.6531. Min Act: -0.0000

Data Index: 686198 (The Pile)

Max Activating Token Index: 94

Text #12

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.5360. Min Act: -0.0000

Data Index: 1650702 (The Pile)

Max Activating Token Index: 209

Text #13

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.6293. Min Act: -0.0000

Data Index: 350463 (The Pile)

Max Activating Token Index: 523

Text #14

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.7587. Min Act: -0.0000

Data Index: 1102177 (The Pile)

Max Activating Token Index: 677

Text #15

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.5779. Min Act: -0.0000

Data Index: 641214 (The Pile)

Max Activating Token Index: 126

Text #16

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.8196. Min Act: -0.0000

Data Index: 1216046 (The Pile)

Max Activating Token Index: 702

Text #17

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.7961. Min Act: -0.0000

Data Index: 353643 (The Pile)

Max Activating Token Index: 41

Text #18

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.5138. Min Act: -0.0000

Data Index: 40734 (The Pile)

Max Activating Token Index: 804

Text #19

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.8667. Min Act: -0.0000

Data Index: 1822095 (The Pile)

Max Activating Token Index: 70