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

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

Neuron 1052 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.6226. Min Act: -0.0000

Data Index: 962652 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.6084. Min Act: -0.0000

Data Index: 327466 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.6064. Min Act: -0.0000

Data Index: 573905 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5532. Min Act: -0.0000

Data Index: 97882 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.6346. Min Act: -0.0000

Data Index: 739721 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5158. Min Act: -0.0000

Data Index: 465854 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5123. Min Act: -0.0000

Data Index: 708244 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5152. Min Act: -0.0000

Data Index: 456745 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4659. Min Act: -0.0000

Data Index: 241026 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4312. Min Act: -0.0000

Data Index: 225389 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4583. Min Act: -0.0000

Data Index: 477840 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4806. Min Act: -0.0000

Data Index: 796102 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1240920 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4465. Min Act: -0.0000

Data Index: 805258 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1054277 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4502. Min Act: -0.0000

Data Index: 538038 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.3990. Min Act: -0.0000

Data Index: 562742 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4213. Min Act: -0.0000

Data Index: 1429077 (Python Code)

Max Activating Token Index: 639

Text #18

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.3895. Min Act: -0.0000

Data Index: 406931 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.3866. Min Act: -0.0000

Data Index: 494835 (C4 (Web Text))

Max Activating Token Index: 560