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

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

Neuron 3478 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0502. Min Act: -0.0003

Data Index: 18062 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0432. Min Act: -0.0003

Data Index: 848873 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0348. Min Act: -0.0003

Data Index: 1146822 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0449. Min Act: -0.0003

Data Index: 13146 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0438. Min Act: -0.0003

Data Index: 162613 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0433. Min Act: -0.0004

Data Index: 300100 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0460. Min Act: -0.0003

Data Index: 581615 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0424. Min Act: -0.0003

Data Index: 1233545 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0419. Min Act: -0.0003

Data Index: 957438 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1269330 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1049287 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0488. Min Act: -0.0003

Data Index: 94477 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0354. Min Act: -0.0003

Data Index: 479318 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0485. Min Act: -0.0003

Data Index: 811156 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1082742 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0435. Min Act: -0.0003

Data Index: 575327 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0452. Min Act: -0.0003

Data Index: 586445 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0414. Min Act: -0.0003

Data Index: 375505 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0421. Min Act: -0.0003

Data Index: 67405 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1318346 (C4 (Web Text))

Max Activating Token Index: 145