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

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

Neuron 182 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.4440. Min Act: -0.0001

Data Index: 658561 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.4063. Min Act: -0.0001

Data Index: 463810 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3689. Min Act: -0.0001

Data Index: 740469 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3784. Min Act: -0.0001

Data Index: 946196 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3399. Min Act: -0.0001

Data Index: 633032 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3639. Min Act: -0.0001

Data Index: 1188635 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3597. Min Act: -0.0001

Data Index: 1223421 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3604. Min Act: -0.0001

Data Index: 653903 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1081161 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3485. Min Act: -0.0001

Data Index: 920158 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3471. Min Act: -0.0001

Data Index: 228008 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3322. Min Act: -0.0001

Data Index: 699322 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3626. Min Act: -0.0001

Data Index: 166018 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3456. Min Act: -0.0001

Data Index: 19254 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3200. Min Act: -0.0001

Data Index: 196156 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3001. Min Act: -0.0001

Data Index: 315198 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3486. Min Act: -0.0001

Data Index: 290491 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3294. Min Act: -0.0001

Data Index: 960260 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3489. Min Act: -0.0001

Data Index: 363382 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 0.4440. Min Range: -0.4440

Max Act: 0.3205. Min Act: -0.0001

Data Index: 294951 (C4 (Web Text))

Max Activating Token Index: 782