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

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

Neuron 1620 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2782. Min Act: -0.0001

Data Index: 358608 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2793. Min Act: -0.0001

Data Index: 182841 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2623. Min Act: -0.0001

Data Index: 268065 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2338. Min Act: -0.0001

Data Index: 809788 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2445. Min Act: -0.0001

Data Index: 1020877 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2339. Min Act: -0.0001

Data Index: 200871 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2345. Min Act: -0.0001

Data Index: 448708 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2385. Min Act: -0.0001

Data Index: 1067152 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2321. Min Act: -0.0001

Data Index: 1222325 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2325. Min Act: -0.0001

Data Index: 726299 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2373. Min Act: -0.0001

Data Index: 540181 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2191. Min Act: -0.0001

Data Index: 1134132 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2190. Min Act: -0.0001

Data Index: 1003391 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2158. Min Act: -0.0001

Data Index: 210677 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2142. Min Act: -0.0001

Data Index: 905563 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2113. Min Act: -0.0001

Data Index: 394646 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2164. Min Act: -0.0001

Data Index: 1088152 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2088. Min Act: -0.0001

Data Index: 60147 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2158. Min Act: -0.0001

Data Index: 172016 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1974. Min Act: -0.0001

Data Index: 92628 (C4 (Web Text))

Max Activating Token Index: 1015