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

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

Neuron 171 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: 0.0413. Min Range: -0.0413

Max Act: 0.0413. Min Act: -0.0004

Data Index: 821986 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0359. Min Act: -0.0004

Data Index: 82220 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0355. Min Act: -0.0004

Data Index: 52923 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0330. Min Act: -0.0004

Data Index: 1188172 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0348. Min Act: -0.0004

Data Index: 1111678 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0327. Min Act: -0.0004

Data Index: 715484 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0309. Min Act: -0.0004

Data Index: 407091 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0321. Min Act: -0.0004

Data Index: 595403 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0315. Min Act: -0.0004

Data Index: 630724 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0316. Min Act: -0.0004

Data Index: 187802 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0288. Min Act: -0.0004

Data Index: 908469 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0311. Min Act: -0.0004

Data Index: 1222269 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0317. Min Act: -0.0004

Data Index: 1109256 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0317. Min Act: -0.0004

Data Index: 1067415 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0309. Min Act: -0.0004

Data Index: 459138 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0299. Min Act: -0.0004

Data Index: 1351873 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0327. Min Act: -0.0004

Data Index: 442076 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0290. Min Act: -0.0004

Data Index: 1308096 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0289. Min Act: -0.0004

Data Index: 980461 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0293. Min Act: -0.0004

Data Index: 1057242 (C4 (Web Text))

Max Activating Token Index: 137