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

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

Neuron 51 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.4459. Min Act: -0.0000

Data Index: 599650 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.4257. Min Act: -0.0000

Data Index: 285114 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.4271. Min Act: -0.0000

Data Index: 178755 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.4044. Min Act: -0.0000

Data Index: 149303 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3838. Min Act: -0.0000

Data Index: 325965 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1195278 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3816. Min Act: -0.0000

Data Index: 32040 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3852. Min Act: -0.0000

Data Index: 138865 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3906. Min Act: -0.0000

Data Index: 887521 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3678. Min Act: -0.0000

Data Index: 598327 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3654. Min Act: -0.0000

Data Index: 428135 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1324920 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1053208 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3688. Min Act: -0.0000

Data Index: 278023 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1338365 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3308. Min Act: -0.0000

Data Index: 843884 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3502. Min Act: -0.0000

Data Index: 716173 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1069667 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3317. Min Act: -0.0000

Data Index: 987634 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.4459. Min Range: -0.4459

Max Act: 0.3515. Min Act: -0.0000

Data Index: 331965 (C4 (Web Text))

Max Activating Token Index: 306