Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1145 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5277. Min Act: -0.0003

Data Index: 1042321 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5055. Min Act: -0.0003

Data Index: 41481 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5030. Min Act: -0.0003

Data Index: 587447 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4737. Min Act: -0.0003

Data Index: 287800 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4277. Min Act: -0.0003

Data Index: 790891 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4639. Min Act: -0.0003

Data Index: 226365 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4213. Min Act: -0.0003

Data Index: 785488 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4662. Min Act: -0.0003

Data Index: 1245369 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4520. Min Act: -0.0003

Data Index: 1023085 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4645. Min Act: -0.0003

Data Index: 356364 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4869. Min Act: -0.0003

Data Index: 531935 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4310. Min Act: -0.0003

Data Index: 1058600 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4699. Min Act: -0.0003

Data Index: 630535 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4539. Min Act: -0.0003

Data Index: 414967 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4270. Min Act: -0.0003

Data Index: 208961 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4236. Min Act: -0.0003

Data Index: 51902 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4172. Min Act: -0.0003

Data Index: 313807 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4163. Min Act: -0.0003

Data Index: 1087810 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4372. Min Act: -0.0003

Data Index: 118312 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4384. Min Act: -0.0003

Data Index: 219549 (C4 (Web Text))

Max Activating Token Index: 438