Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 217 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0469. Min Act: -0.0003

Data Index: 864470 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0400. Min Act: -0.0003

Data Index: 698234 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0391. Min Act: -0.0003

Data Index: 382797 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0393. Min Act: -0.0003

Data Index: 352002 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0386. Min Act: -0.0004

Data Index: 1157248 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1049802 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0372. Min Act: -0.0003

Data Index: 1170017 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0375. Min Act: -0.0003

Data Index: 460510 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0361. Min Act: -0.0003

Data Index: 653523 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1351044 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0358. Min Act: -0.0003

Data Index: 888539 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0337. Min Act: -0.0004

Data Index: 1046021 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0344. Min Act: -0.0003

Data Index: 702316 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0345. Min Act: -0.0003

Data Index: 62650 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1221815 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0337. Min Act: -0.0003

Data Index: 410171 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0344. Min Act: -0.0003

Data Index: 122868 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1023212 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1486449 (Python Code)

Max Activating Token Index: 288

Text #19

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0331. Min Act: -0.0003

Data Index: 425643 (C4 (Web Text))

Max Activating Token Index: 749