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

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

Neuron 645 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3303. Min Act: -0.0001

Data Index: 472445 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2549. Min Act: -0.0001

Data Index: 708079 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2584. Min Act: -0.0001

Data Index: 627065 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2534. Min Act: -0.0001

Data Index: 1111958 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2327. Min Act: -0.0001

Data Index: 825086 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2315. Min Act: -0.0001

Data Index: 254436 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2383. Min Act: -0.0001

Data Index: 1282660 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2325. Min Act: -0.0001

Data Index: 141130 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2220. Min Act: -0.0001

Data Index: 804709 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2271. Min Act: -0.0001

Data Index: 626943 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2270. Min Act: -0.0001

Data Index: 746316 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2254. Min Act: -0.0001

Data Index: 338893 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2267. Min Act: -0.0001

Data Index: 39681 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.1955. Min Act: -0.0001

Data Index: 1356716 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2219. Min Act: -0.0001

Data Index: 512084 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2388. Min Act: -0.0001

Data Index: 290070 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2130. Min Act: -0.0001

Data Index: 991653 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2072. Min Act: -0.0001

Data Index: 648229 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1112689 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2088. Min Act: -0.0001

Data Index: 367767 (C4 (Web Text))

Max Activating Token Index: 283