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

Dataset: The Pile

Neuron 2378 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: 0.1363. Min Range: -0.1363

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1351598 (The Pile)

Max Activating Token Index: 888

Text #1

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1262. Min Act: -0.0000

Data Index: 135566 (The Pile)

Max Activating Token Index: 706

Text #2

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1361. Min Act: -0.0000

Data Index: 831464 (The Pile)

Max Activating Token Index: 773

Text #3

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1182. Min Act: -0.0000

Data Index: 229762 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1264. Min Act: -0.0000

Data Index: 1396903 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1191. Min Act: -0.0000

Data Index: 377752 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1242. Min Act: -0.0000

Data Index: 1467781 (The Pile)

Max Activating Token Index: 448

Text #7

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1747445 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1113. Min Act: -0.0000

Data Index: 815154 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1155018 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1184305 (The Pile)

Max Activating Token Index: 639

Text #11

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1192. Min Act: -0.0000

Data Index: 148977 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1069. Min Act: -0.0000

Data Index: 859443 (The Pile)

Max Activating Token Index: 616

Text #13

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1646032 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1034. Min Act: -0.0000

Data Index: 378081 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1051006 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1143. Min Act: -0.0000

Data Index: 1688041 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1862165 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1053036 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1197. Min Act: -0.0000

Data Index: 768662 (The Pile)

Max Activating Token Index: 720