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

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

Neuron 4363 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.7338. Min Act: -0.0000

Data Index: 1030692 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.5630. Min Act: -0.0000

Data Index: 122840 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.5524. Min Act: -0.0000

Data Index: 209233 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.5297. Min Act: -0.0000

Data Index: 1219719 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.4976. Min Act: -0.0000

Data Index: 748316 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.4456. Min Act: -0.0000

Data Index: 762448 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.5095. Min Act: -0.0000

Data Index: 325335 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.4293. Min Act: -0.0000

Data Index: 270230 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.3361. Min Act: -0.0000

Data Index: 707792 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.2945. Min Act: 0.0000

Data Index: 1110035 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.3720. Min Act: -0.0000

Data Index: 221916 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.2382. Min Act: -0.0000

Data Index: 1149495 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.2392. Min Act: -0.0000

Data Index: 1164067 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.2379. Min Act: -0.0000

Data Index: 867911 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.1560. Min Act: -0.0000

Data Index: 195874 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.2109. Min Act: -0.0000

Data Index: 316184 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.2079. Min Act: -0.0000

Data Index: 779543 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.1936. Min Act: -0.0000

Data Index: 43470 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.2711. Min Act: -0.0000

Data Index: 178094 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.1873. Min Act: -0.0000

Data Index: 277861 (C4 (Web Text))

Max Activating Token Index: 744