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

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

Neuron 1885 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: 0.4994. Min Range: -0.4994

Max Act: 0.4994. Min Act: -0.0002

Data Index: 270177 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3939. Min Act: -0.0002

Data Index: 423266 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3593. Min Act: -0.0002

Data Index: 607588 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3162. Min Act: -0.0002

Data Index: 617921 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2448. Min Act: -0.0002

Data Index: 457006 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2728. Min Act: -0.0002

Data Index: 633081 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2757. Min Act: -0.0002

Data Index: 597835 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2344. Min Act: -0.0002

Data Index: 549103 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2314. Min Act: -0.0002

Data Index: 46112 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2404. Min Act: -0.0002

Data Index: 1171576 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2376. Min Act: -0.0002

Data Index: 691176 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2326. Min Act: -0.0002

Data Index: 851452 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2387. Min Act: -0.0002

Data Index: 1332707 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2353. Min Act: -0.0002

Data Index: 229157 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2392. Min Act: -0.0002

Data Index: 646798 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2316. Min Act: -0.0002

Data Index: 268733 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2359. Min Act: -0.0002

Data Index: 754815 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2165. Min Act: -0.0002

Data Index: 832862 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2409. Min Act: -0.0002

Data Index: 492725 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.2358. Min Act: -0.0002

Data Index: 420646 (C4 (Web Text))

Max Activating Token Index: 219