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

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

Neuron 3947 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: 0.4187. Min Range: -0.4187

Max Act: 0.4187. Min Act: -0.0000

Data Index: 435019 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.4009. Min Act: -0.0000

Data Index: 871253 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3984. Min Act: -0.0000

Data Index: 758840 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1336457 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3872. Min Act: -0.0000

Data Index: 779937 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3834. Min Act: -0.0000

Data Index: 135383 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3825. Min Act: -0.0000

Data Index: 669312 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3768. Min Act: -0.0000

Data Index: 117144 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3656. Min Act: -0.0000

Data Index: 1173812 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3524. Min Act: -0.0000

Data Index: 262000 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3528. Min Act: -0.0000

Data Index: 836623 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1029819 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3276. Min Act: 0.0000

Data Index: 250603 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3280. Min Act: -0.0000

Data Index: 893705 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1166799 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3286. Min Act: 0.0000

Data Index: 861942 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3370. Min Act: -0.0000

Data Index: 165660 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3280. Min Act: -0.0000

Data Index: 233445 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3209. Min Act: 0.0000

Data Index: 930934 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3190. Min Act: -0.0000

Data Index: 504760 (C4 (Web Text))

Max Activating Token Index: 732