Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 628 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0345. Min Act: -0.0006

Data Index: 899676 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0330. Min Act: -0.0005

Data Index: 262576 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0322. Min Act: -0.0005

Data Index: 1237029 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0324. Min Act: -0.0005

Data Index: 584815 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0323. Min Act: -0.0005

Data Index: 545755 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0329. Min Act: -0.0005

Data Index: 985631 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0321. Min Act: -0.0006

Data Index: 60420 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0311. Min Act: -0.0005

Data Index: 641583 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0309. Min Act: -0.0005

Data Index: 897713 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0290. Min Act: -0.0006

Data Index: 961243 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0287. Min Act: -0.0005

Data Index: 124045 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0284. Min Act: -0.0005

Data Index: 21534 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0277. Min Act: -0.0005

Data Index: 350650 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0277. Min Act: -0.0005

Data Index: 568367 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0272. Min Act: -0.0005

Data Index: 730964 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0271. Min Act: -0.0005

Data Index: 964586 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0266. Min Act: -0.0005

Data Index: 234811 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0259. Min Act: -0.0005

Data Index: 386823 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0257. Min Act: -0.0005

Data Index: 1147327 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0257. Min Act: -0.0005

Data Index: 122931 (C4 (Web Text))

Max Activating Token Index: 812