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

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

Neuron 3101 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: 0.4339. Min Range: -0.4339

Max Act: 0.4339. Min Act: -0.0000

Data Index: 187287 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3554. Min Act: -0.0001

Data Index: 602504 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3541. Min Act: -0.0001

Data Index: 793006 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1541724 (Python Code)

Max Activating Token Index: 386

Text #4

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1063244 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1644218 (Python Code)

Max Activating Token Index: 41

Text #6

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3313. Min Act: -0.0001

Data Index: 73680 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3424. Min Act: -0.0000

Data Index: 388037 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3490. Min Act: -0.0000

Data Index: 1539029 (Python Code)

Max Activating Token Index: 61

Text #9

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1575946 (Python Code)

Max Activating Token Index: 994

Text #10

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3613. Min Act: -0.0001

Data Index: 44517 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1164892 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3449. Min Act: -0.0000

Data Index: 1401381 (Python Code)

Max Activating Token Index: 990

Text #13

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3221. Min Act: -0.0001

Data Index: 856654 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1616894 (Python Code)

Max Activating Token Index: 18

Text #15

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1607150 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3260. Min Act: -0.0001

Data Index: 917259 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1255377 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1504728 (Python Code)

Max Activating Token Index: 768

Text #19

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3205. Min Act: -0.0000

Data Index: 358427 (C4 (Web Text))

Max Activating Token Index: 107