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

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

Neuron 4195 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1329446 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1471805 (Python Code)

Max Activating Token Index: 960

Text #2

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1611647 (Python Code)

Max Activating Token Index: 800

Text #3

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0284. Min Act: -0.0002

Data Index: 529493 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1089198 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0277. Min Act: -0.0002

Data Index: 695391 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0305. Min Act: -0.0002

Data Index: 1169164 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1032517 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0254. Min Act: -0.0002

Data Index: 390006 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1109077 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0304. Min Act: -0.0002

Data Index: 481131 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0232. Min Act: -0.0002

Data Index: 148829 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0257. Min Act: -0.0002

Data Index: 680188 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0237. Min Act: -0.0002

Data Index: 511987 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0211. Min Act: -0.0002

Data Index: 653253 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0227. Min Act: -0.0002

Data Index: 491981 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1367954 (Python Code)

Max Activating Token Index: 513

Text #17

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0238. Min Act: -0.0002

Data Index: 148971 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0203. Min Act: -0.0002

Data Index: 386766 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0231. Min Act: -0.0002

Data Index: 54053 (C4 (Web Text))

Max Activating Token Index: 623