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

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

Neuron 543 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1255799 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.7257. Min Act: -0.0000

Data Index: 567941 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.7148. Min Act: -0.0000

Data Index: 903153 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.7120. Min Act: -0.0000

Data Index: 924823 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1209899 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.7033. Min Act: -0.0000

Data Index: 304653 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.7478. Min Act: -0.0000

Data Index: 468168 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.6806. Min Act: -0.0000

Data Index: 24474 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.6595. Min Act: -0.0000

Data Index: 959927 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.6542. Min Act: -0.0000

Data Index: 312334 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.6575. Min Act: -0.0000

Data Index: 841431 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.6262. Min Act: -0.0000

Data Index: 144679 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.6488. Min Act: -0.0000

Data Index: 946488 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.6252. Min Act: -0.0000

Data Index: 580067 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.6234. Min Act: -0.0000

Data Index: 412280 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.6434. Min Act: -0.0000

Data Index: 322959 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.6399. Min Act: -0.0000

Data Index: 468012 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.6157. Min Act: -0.0000

Data Index: 468514 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.6149. Min Act: -0.0000

Data Index: 926549 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.7691. Min Range: -0.7691

Max Act: 0.6068. Min Act: -0.0000

Data Index: 380576 (C4 (Web Text))

Max Activating Token Index: 232