Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1453 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0364. Min Act: -0.0003

Data Index: 522308 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0359. Min Act: -0.0002

Data Index: 997963 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0003

Data Index: 986178 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0350. Min Act: -0.0003

Data Index: 680829 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0348. Min Act: -0.0003

Data Index: 973407 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1282075 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0348. Min Act: -0.0003

Data Index: 277298 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0334. Min Act: -0.0003

Data Index: 257820 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1039523 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0329. Min Act: -0.0003

Data Index: 670768 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0319. Min Act: -0.0002

Data Index: 619406 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0313. Min Act: -0.0003

Data Index: 388378 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0321. Min Act: -0.0003

Data Index: 631389 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1262085 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1189710 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1280605 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0295. Min Act: -0.0004

Data Index: 369749 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0294. Min Act: -0.0003

Data Index: 185220 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1211345 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0294. Min Act: -0.0003

Data Index: 913483 (C4 (Web Text))

Max Activating Token Index: 605