Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 403 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.3346. Min Act: -0.0000

Data Index: 214119 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.0952. Min Act: -0.0000

Data Index: 612921 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.2110. Min Act: -0.0000

Data Index: 91216 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.1610. Min Act: -0.0000

Data Index: 1239551 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.1322. Min Act: -0.0000

Data Index: 441119 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.0678. Min Act: -0.0000

Data Index: 1120200 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.8377. Min Act: -0.0000

Data Index: 795264 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.9882. Min Act: -0.0000

Data Index: 362939 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.9635. Min Act: -0.0000

Data Index: 196430 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 3.3346. Min Range: -3.3346

Max Act: 3.0910. Min Act: -0.0000

Data Index: 1350369 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.9211. Min Act: -0.0000

Data Index: 481241 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.8904. Min Act: -0.0000

Data Index: 75408 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.9102. Min Act: -0.0000

Data Index: 1305782 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.8423. Min Act: -0.0000

Data Index: 924329 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.8365. Min Act: -0.0000

Data Index: 830184 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.8239. Min Act: -0.0000

Data Index: 898365 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.8269. Min Act: -0.0000

Data Index: 453186 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.7855. Min Act: -0.0000

Data Index: 974566 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.7908. Min Act: -0.0000

Data Index: 443507 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 3.3346. Min Range: -3.3346

Max Act: 2.6518. Min Act: -0.0000

Data Index: 600662 (C4 (Web Text))

Max Activating Token Index: 1022