Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5254 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0000

Data Index: 134614 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0490. Min Act: -0.0000

Data Index: 635177 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0423. Min Act: -0.0000

Data Index: 86608 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0467. Min Act: -0.0000

Data Index: 702107 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0399. Min Act: -0.0000

Data Index: 661692 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0425. Min Act: -0.0000

Data Index: 348692 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0390. Min Act: -0.0001

Data Index: 879950 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0399. Min Act: -0.0001

Data Index: 876947 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0414. Min Act: -0.0000

Data Index: 181690 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0407. Min Act: -0.0000

Data Index: 406666 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0409. Min Act: -0.0000

Data Index: 668360 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0388. Min Act: -0.0000

Data Index: 1488749 (Python Code)

Max Activating Token Index: 156

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0406. Min Act: -0.0000

Data Index: 1253178 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0378. Min Act: -0.0000

Data Index: 1299166 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0380. Min Act: -0.0000

Data Index: 305087 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0418. Min Act: -0.0000

Data Index: 422094 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0379. Min Act: -0.0000

Data Index: 1286735 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0364. Min Act: -0.0000

Data Index: 741483 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0345. Min Act: -0.0000

Data Index: 1601565 (Python Code)

Max Activating Token Index: 236

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0355. Min Act: -0.0000

Data Index: 140185 (C4 (Web Text))

Max Activating Token Index: 612