Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3071 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0335. Min Act: -0.0004

Data Index: 930901 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0308. Min Act: -0.0004

Data Index: 803353 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0208. Min Act: -0.0004

Data Index: 431756 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0265. Min Act: -0.0004

Data Index: 298712 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0215. Min Act: -0.0004

Data Index: 983592 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0302. Min Act: -0.0004

Data Index: 711715 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0312. Min Act: -0.0004

Data Index: 57949 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0332. Min Act: -0.0004

Data Index: 595865 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0318. Min Act: -0.0004

Data Index: 1634731 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0317. Min Act: -0.0004

Data Index: 664683 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0258. Min Act: -0.0004

Data Index: 507485 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0290. Min Act: -0.0004

Data Index: 91963 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0235. Min Act: -0.0004

Data Index: 735939 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0249. Min Act: -0.0004

Data Index: 901979 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0327. Min Act: -0.0004

Data Index: 913171 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0261. Min Act: -0.0004

Data Index: 1202078 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0289. Min Act: -0.0004

Data Index: 492468 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0265. Min Act: -0.0004

Data Index: 352616 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0272. Min Act: -0.0004

Data Index: 88989 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0296. Min Act: -0.0004

Data Index: 547485 (C4 (Web Text))

Max Activating Token Index: 2