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

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

Neuron 104 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0003

Data Index: 117296 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0307. Min Act: -0.0003

Data Index: 537957 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0271. Min Act: -0.0003

Data Index: 656375 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0269. Min Act: -0.0003

Data Index: 888584 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0268. Min Act: -0.0003

Data Index: 68422 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0260. Min Act: -0.0003

Data Index: 235485 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1059937 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0263. Min Act: -0.0003

Data Index: 502959 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0262. Min Act: -0.0003

Data Index: 446619 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0262. Min Act: -0.0003

Data Index: 941043 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0263. Min Act: -0.0003

Data Index: 711120 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1000942 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0253. Min Act: -0.0003

Data Index: 710244 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1020760 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0251. Min Act: -0.0003

Data Index: 287465 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0249. Min Act: -0.0003

Data Index: 764064 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0243. Min Act: -0.0002

Data Index: 478099 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0246. Min Act: -0.0002

Data Index: 446481 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1003910 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0245. Min Act: -0.0002

Data Index: 934929 (C4 (Web Text))

Max Activating Token Index: 570