Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1203 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.5836. Min Act: -0.0000

Data Index: 729996 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4990. Min Act: -0.0000

Data Index: 1338334 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.5384. Min Act: -0.0000

Data Index: 411217 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4894. Min Act: -0.0000

Data Index: 958476 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.5146. Min Act: -0.0001

Data Index: 857640 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4459. Min Act: -0.0000

Data Index: 71893 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4710. Min Act: -0.0000

Data Index: 472560 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1166180 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4204. Min Act: -0.0000

Data Index: 368587 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4356. Min Act: -0.0000

Data Index: 893088 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4442. Min Act: -0.0001

Data Index: 1176396 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4177. Min Act: -0.0001

Data Index: 533770 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4222. Min Act: -0.0001

Data Index: 1337671 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4590. Min Act: -0.0001

Data Index: 1170870 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4252. Min Act: -0.0000

Data Index: 78590 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3981. Min Act: -0.0001

Data Index: 391150 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4099. Min Act: -0.0000

Data Index: 979153 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4305. Min Act: -0.0000

Data Index: 715920 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1283995 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3849. Min Act: -0.0001

Data Index: 1342324 (C4 (Web Text))

Max Activating Token Index: 132