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

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

Neuron 2764 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2628. Min Act: -0.0001

Data Index: 1063855 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2511. Min Act: -0.0000

Data Index: 304619 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2344. Min Act: -0.0001

Data Index: 810619 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2253. Min Act: -0.0001

Data Index: 427774 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2441. Min Act: -0.0001

Data Index: 357799 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2333. Min Act: -0.0000

Data Index: 91303 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1320173 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2463. Min Act: -0.0001

Data Index: 276277 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2356. Min Act: -0.0001

Data Index: 1037056 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2271. Min Act: -0.0001

Data Index: 1003855 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2163. Min Act: -0.0000

Data Index: 915526 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2221. Min Act: -0.0000

Data Index: 85148 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1181429 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2298. Min Act: -0.0001

Data Index: 686043 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2089. Min Act: -0.0001

Data Index: 999389 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2090. Min Act: -0.0001

Data Index: 513651 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2146. Min Act: -0.0000

Data Index: 1062205 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1903. Min Act: -0.0001

Data Index: 441332 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2052. Min Act: -0.0000

Data Index: 210152 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1964. Min Act: -0.0001

Data Index: 292381 (C4 (Web Text))

Max Activating Token Index: 795