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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2356 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5138. Min Range: -1.5138

Max Act: 1.5138. Min Act: -0.0000

Data Index: 381076 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 1.5138. Min Range: -1.5138

Max Act: 1.4975. Min Act: -0.0000

Data Index: 39003 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.8978. Min Act: -0.0000

Data Index: 763018 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.8357. Min Act: -0.0000

Data Index: 761849 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1263614 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.8805. Min Act: -0.0000

Data Index: 651141 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.8379. Min Act: -0.0000

Data Index: 891980 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.7559. Min Act: 0.0000

Data Index: 1111919 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1208264 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.7173. Min Act: -0.0000

Data Index: 754687 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.6895. Min Act: 0.0001

Data Index: 1214472 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.6952. Min Act: -0.0000

Data Index: 737467 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.7122. Min Act: -0.0000

Data Index: 174477 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.6823. Min Act: -0.0000

Data Index: 335961 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.6852. Min Act: -0.0000

Data Index: 520814 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.6903. Min Act: -0.0000

Data Index: 330990 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.6666. Min Act: -0.0000

Data Index: 336063 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.6320. Min Act: -0.0000

Data Index: 757941 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.6338. Min Act: -0.0000

Data Index: 95020 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 1.5138. Min Range: -1.5138

Max Act: 0.6367. Min Act: -0.0000

Data Index: 100727 (C4 (Web Text))

Max Activating Token Index: 758