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

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

Neuron 2785 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0382. Min Act: -0.0002

Data Index: 341502 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1273841 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1150289 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0355. Min Act: -0.0002

Data Index: 267445 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1298179 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0343. Min Act: -0.0002

Data Index: 535327 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0347. Min Act: -0.0002

Data Index: 544420 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0346. Min Act: -0.0002

Data Index: 853091 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1149199 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0325. Min Act: -0.0002

Data Index: 975964 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1152058 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1067446 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0331. Min Act: -0.0002

Data Index: 173117 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1496407 (Python Code)

Max Activating Token Index: 830

Text #14

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0319. Min Act: -0.0002

Data Index: 273204 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1262980 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1227104 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1159923 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0307. Min Act: -0.0002

Data Index: 160796 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1171060 (C4 (Web Text))

Max Activating Token Index: 460