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

Dataset: The Pile

Neuron 1661 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.6577. Min Range: -7.6577

Max Act: 7.6577. Min Act: -0.0000

Data Index: 275519 (The Pile)

Max Activating Token Index: 864

Text #1

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.5676. Min Act: -0.0000

Data Index: 1432704 (The Pile)

Max Activating Token Index: 68

Text #2

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.2946. Min Act: -0.0000

Data Index: 1515127 (The Pile)

Max Activating Token Index: 201

Text #3

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.4500. Min Act: -0.0000

Data Index: 539508 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.4020. Min Act: -0.0000

Data Index: 1136080 (The Pile)

Max Activating Token Index: 537

Text #5

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.3686. Min Act: -0.0000

Data Index: 1183817 (The Pile)

Max Activating Token Index: 270

Text #6

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.4744. Min Act: -0.0000

Data Index: 1126585 (The Pile)

Max Activating Token Index: 91

Text #7

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.4557. Min Act: -0.0000

Data Index: 1809295 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.2204. Min Act: -0.0000

Data Index: 1859231 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.3626. Min Act: -0.0000

Data Index: 674556 (The Pile)

Max Activating Token Index: 66

Text #10

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.1103. Min Act: -0.0000

Data Index: 1097220 (The Pile)

Max Activating Token Index: 19

Text #11

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.0911. Min Act: -0.0000

Data Index: 1675413 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.0509. Min Act: -0.0000

Data Index: 790930 (The Pile)

Max Activating Token Index: 181

Text #13

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.5473. Min Act: -0.0000

Data Index: 771505 (The Pile)

Max Activating Token Index: 193

Text #14

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.1192. Min Act: -0.0000

Data Index: 754737 (The Pile)

Max Activating Token Index: 465

Text #15

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.0394. Min Act: -0.0000

Data Index: 1011187 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.0458. Min Act: -0.0000

Data Index: 497363 (The Pile)

Max Activating Token Index: 190

Text #17

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.2499. Min Act: -0.0000

Data Index: 1643777 (The Pile)

Max Activating Token Index: 54

Text #18

Max Range: 7.6577. Min Range: -7.6577

Max Act: 5.7928. Min Act: -0.0000

Data Index: 511937 (The Pile)

Max Activating Token Index: 419

Text #19

Max Range: 7.6577. Min Range: -7.6577

Max Act: 6.0266. Min Act: -0.0000

Data Index: 1621692 (The Pile)

Max Activating Token Index: 713