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

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

Neuron 2733 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0003

Data Index: 633931 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1258000 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0283. Min Act: -0.0003

Data Index: 920005 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0278. Min Act: -0.0003

Data Index: 729714 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0277. Min Act: -0.0003

Data Index: 815781 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1555171 (Python Code)

Max Activating Token Index: 853

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1041874 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0267. Min Act: -0.0003

Data Index: 625770 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0268. Min Act: -0.0003

Data Index: 799639 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1475100 (Python Code)

Max Activating Token Index: 45

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0260. Min Act: -0.0003

Data Index: 486288 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0254. Min Act: -0.0004

Data Index: 1076824 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1549017 (Python Code)

Max Activating Token Index: 84

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0261. Min Act: -0.0003

Data Index: 236043 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0260. Min Act: -0.0003

Data Index: 443483 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0242. Min Act: -0.0004

Data Index: 1453685 (Python Code)

Max Activating Token Index: 367

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0245. Min Act: -0.0003

Data Index: 495634 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0244. Min Act: -0.0003

Data Index: 33856 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0243. Min Act: -0.0003

Data Index: 28930 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0247. Min Act: -0.0003

Data Index: 697661 (C4 (Web Text))

Max Activating Token Index: 3