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

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

Neuron 678 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: 0.0461. Min Range: -0.0461

Max Act: 0.0461. Min Act: -0.0003

Data Index: 593944 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0387. Min Act: -0.0002

Data Index: 125935 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0374. Min Act: -0.0003

Data Index: 1014477 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0375. Min Act: -0.0003

Data Index: 1334438 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0366. Min Act: -0.0003

Data Index: 396375 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0347. Min Act: -0.0003

Data Index: 376358 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0344. Min Act: -0.0002

Data Index: 331401 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1388597 (Python Code)

Max Activating Token Index: 220

Text #8

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0348. Min Act: -0.0002

Data Index: 88587 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1115821 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0350. Min Act: -0.0002

Data Index: 349505 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1228560 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0335. Min Act: -0.0003

Data Index: 117520 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0322. Min Act: -0.0002

Data Index: 599053 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1193600 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1602657 (Python Code)

Max Activating Token Index: 201

Text #16

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0334. Min Act: -0.0003

Data Index: 687612 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0325. Min Act: -0.0003

Data Index: 403137 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1084708 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0323. Min Act: -0.0003

Data Index: 861987 (C4 (Web Text))

Max Activating Token Index: 844