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

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

Neuron 261 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: 0.6301. Min Range: -0.6301

Max Act: 0.6301. Min Act: -0.0003

Data Index: 800962 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.6065. Min Act: -0.0003

Data Index: 89463 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5863. Min Act: -0.0002

Data Index: 377454 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.6167. Min Act: -0.0002

Data Index: 738177 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5777. Min Act: -0.0003

Data Index: 9516 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5857. Min Act: -0.0002

Data Index: 454381 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5574. Min Act: -0.0003

Data Index: 1208179 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5446. Min Act: -0.0003

Data Index: 259593 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5459. Min Act: -0.0003

Data Index: 512612 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5704. Min Act: -0.0002

Data Index: 381671 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5441. Min Act: -0.0003

Data Index: 573681 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5439. Min Act: -0.0002

Data Index: 788784 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5388. Min Act: -0.0002

Data Index: 549647 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5403. Min Act: -0.0002

Data Index: 1309114 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5389. Min Act: -0.0002

Data Index: 223146 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5333. Min Act: -0.0003

Data Index: 890658 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5418. Min Act: -0.0002

Data Index: 1038265 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4984. Min Act: -0.0003

Data Index: 1232608 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5228. Min Act: -0.0003

Data Index: 734716 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5398. Min Act: -0.0003

Data Index: 1182031 (C4 (Web Text))

Max Activating Token Index: 369