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

Dataset: The Pile

Neuron 2195 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: 1.7165. Min Range: -1.7165

Max Act: 1.7165. Min Act: -0.0000

Data Index: 813942 (The Pile)

Max Activating Token Index: 474

Text #1

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.6310. Min Act: -0.0000

Data Index: 341224 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.3669. Min Act: -0.0000

Data Index: 1271104 (The Pile)

Max Activating Token Index: 894

Text #3

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.2252. Min Act: -0.0000

Data Index: 1357095 (The Pile)

Max Activating Token Index: 611

Text #4

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.2243. Min Act: -0.0000

Data Index: 905115 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1734736 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0755. Min Act: -0.0000

Data Index: 152464 (The Pile)

Max Activating Token Index: 945

Text #7

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.1595. Min Act: 0.0000

Data Index: 983904 (The Pile)

Max Activating Token Index: 608

Text #8

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.1269. Min Act: -0.0000

Data Index: 278686 (The Pile)

Max Activating Token Index: 545

Text #9

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0638. Min Act: -0.0000

Data Index: 1593883 (The Pile)

Max Activating Token Index: 768

Text #10

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0255. Min Act: -0.0000

Data Index: 355140 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9512. Min Act: -0.0000

Data Index: 1126907 (The Pile)

Max Activating Token Index: 38

Text #12

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0013. Min Act: -0.0000

Data Index: 1454054 (The Pile)

Max Activating Token Index: 840

Text #13

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0087. Min Act: -0.0000

Data Index: 176039 (The Pile)

Max Activating Token Index: 351

Text #14

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1049229 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9527. Min Act: -0.0000

Data Index: 860689 (The Pile)

Max Activating Token Index: 19

Text #16

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1021025 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1877831 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0602. Min Act: -0.0000

Data Index: 1833620 (The Pile)

Max Activating Token Index: 136

Text #19

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9963. Min Act: -0.0000

Data Index: 1063627 (The Pile)

Max Activating Token Index: 634