Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3211 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0382. Min Act: -0.0001

Data Index: 569381 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0408. Min Act: -0.0001

Data Index: 474562 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0408. Min Act: -0.0001

Data Index: 948442 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0363. Min Act: -0.0001

Data Index: 315335 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0362. Min Act: -0.0001

Data Index: 248850 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0331. Min Act: -0.0001

Data Index: 4063 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0348. Min Act: -0.0001

Data Index: 252964 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0337. Min Act: -0.0001

Data Index: 1212700 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0331. Min Act: -0.0001

Data Index: 280630 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1327091 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1222512 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0292. Min Act: -0.0001

Data Index: 403943 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0324. Min Act: -0.0001

Data Index: 1143287 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0286. Min Act: -0.0001

Data Index: 459176 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0335. Min Act: -0.0001

Data Index: 99845 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1175913 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0291. Min Act: -0.0001

Data Index: 1323811 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1108520 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0298. Min Act: -0.0001

Data Index: 938254 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0259. Min Act: -0.0001

Data Index: 232700 (C4 (Web Text))

Max Activating Token Index: 910