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

Dataset: The Pile

Neuron 4758 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.2369. Min Act: -0.0000

Data Index: 886079 (The Pile)

Max Activating Token Index: 780

Text #1

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.9925. Min Act: -0.0000

Data Index: 174719 (The Pile)

Max Activating Token Index: 397

Text #2

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.5838. Min Act: -0.0000

Data Index: 1601361 (The Pile)

Max Activating Token Index: 550

Text #3

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.6559. Min Act: -0.0000

Data Index: 392099 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.4893. Min Act: -0.0000

Data Index: 1118065 (The Pile)

Max Activating Token Index: 487

Text #5

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.5462. Min Act: -0.0000

Data Index: 1254746 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.6348. Min Act: -0.0000

Data Index: 1259612 (The Pile)

Max Activating Token Index: 732

Text #7

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.4053. Min Act: -0.0000

Data Index: 1505820 (The Pile)

Max Activating Token Index: 117

Text #8

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.6224. Min Act: -0.0000

Data Index: 1495340 (The Pile)

Max Activating Token Index: 257

Text #9

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.3372. Min Act: -0.0000

Data Index: 1996169 (The Pile)

Max Activating Token Index: 342

Text #10

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.4898. Min Act: -0.0000

Data Index: 1752903 (The Pile)

Max Activating Token Index: 327

Text #11

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.3239. Min Act: -0.0000

Data Index: 1170779 (The Pile)

Max Activating Token Index: 229

Text #12

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.2100. Min Act: -0.0000

Data Index: 185464 (The Pile)

Max Activating Token Index: 774

Text #13

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.1700. Min Act: -0.0000

Data Index: 1042665 (The Pile)

Max Activating Token Index: 361

Text #14

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.1678. Min Act: -0.0000

Data Index: 1779253 (The Pile)

Max Activating Token Index: 673

Text #15

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.4265. Min Act: -0.0000

Data Index: 1561143 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.2788. Min Act: -0.0000

Data Index: 104602 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.3871. Min Act: -0.0000

Data Index: 891636 (The Pile)

Max Activating Token Index: 634

Text #18

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.4204. Min Act: -0.0000

Data Index: 841417 (The Pile)

Max Activating Token Index: 420

Text #19

Max Range: 3.9925. Min Range: -3.9925

Max Act: 3.2569. Min Act: -0.0000

Data Index: 568494 (The Pile)

Max Activating Token Index: 500