Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3653 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1283. Min Range: -1.1283

Max Act: 1.1283. Min Act: -0.0000

Data Index: 1582873 (Python Code)

Max Activating Token Index: 614

Text #1

Max Range: 1.1283. Min Range: -1.1283

Max Act: 1.0329. Min Act: -0.0000

Data Index: 443037 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.1283. Min Range: -1.1283

Max Act: 1.0196. Min Act: -0.0000

Data Index: 1003824 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 1.1283. Min Range: -1.1283

Max Act: 1.0576. Min Act: -0.0000

Data Index: 1656735 (Python Code)

Max Activating Token Index: 944

Text #4

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.9922. Min Act: -0.0000

Data Index: 284290 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.8673. Min Act: -0.0000

Data Index: 807667 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.9255. Min Act: -0.0000

Data Index: 31121 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.8911. Min Act: -0.0000

Data Index: 738059 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.8786. Min Act: -0.0000

Data Index: 795295 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1162687 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1047050 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.8217. Min Act: -0.0000

Data Index: 316353 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.8161. Min Act: -0.0000

Data Index: 770536 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.8141. Min Act: -0.0000

Data Index: 608790 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.8101. Min Act: -0.0000

Data Index: 24990 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1294411 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.7960. Min Act: -0.0000

Data Index: 905448 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1635770 (Python Code)

Max Activating Token Index: 1005

Text #18

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.7851. Min Act: -0.0000

Data Index: 983225 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 1.1283. Min Range: -1.1283

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1150858 (C4 (Web Text))

Max Activating Token Index: 899