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

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

Neuron 3590 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1418. Min Act: -0.0003

Data Index: 201407 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1356. Min Act: -0.0003

Data Index: 152632 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1269. Min Act: -0.0003

Data Index: 473175 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1290. Min Act: -0.0003

Data Index: 612934 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1350. Min Act: -0.0003

Data Index: 310712 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1236. Min Act: -0.0003

Data Index: 483679 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1224. Min Act: -0.0003

Data Index: 543090 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1202. Min Act: -0.0003

Data Index: 1067785 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1202. Min Act: -0.0003

Data Index: 811322 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1238. Min Act: -0.0003

Data Index: 436143 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1183. Min Act: -0.0003

Data Index: 883042 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1162. Min Act: -0.0003

Data Index: 1243124 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1114. Min Act: -0.0003

Data Index: 597481 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1110. Min Act: -0.0003

Data Index: 810390 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1106. Min Act: -0.0003

Data Index: 22121 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1144. Min Act: -0.0003

Data Index: 775800 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1098. Min Act: -0.0003

Data Index: 446363 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0956. Min Act: -0.0003

Data Index: 403983 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0984. Min Act: -0.0003

Data Index: 239301 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0974. Min Act: -0.0003

Data Index: 834445 (C4 (Web Text))

Max Activating Token Index: 222