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

Dataset: The Pile

Neuron 732 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.9407. Min Act: -0.0000

Data Index: 679996 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1063242 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1711889 (The Pile)

Max Activating Token Index: 576

Text #3

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.8470. Min Act: -0.0000

Data Index: 192953 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1732535 (The Pile)

Max Activating Token Index: 260

Text #5

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1129050 (The Pile)

Max Activating Token Index: 70

Text #6

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1339174 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1956495 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.7153. Min Act: -0.0000

Data Index: 58302 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6835. Min Act: -0.0000

Data Index: 112226 (The Pile)

Max Activating Token Index: 686

Text #10

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1532562 (The Pile)

Max Activating Token Index: 162

Text #11

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6591. Min Act: -0.0000

Data Index: 70227 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1919554 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1279970 (The Pile)

Max Activating Token Index: 825

Text #14

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1457819 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1684934 (The Pile)

Max Activating Token Index: 556

Text #16

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6077. Min Act: -0.0000

Data Index: 667637 (The Pile)

Max Activating Token Index: 727

Text #17

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6219. Min Act: -0.0000

Data Index: 414528 (The Pile)

Max Activating Token Index: 273

Text #18

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.5747. Min Act: -0.0000

Data Index: 965869 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1100692 (The Pile)

Max Activating Token Index: 987