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

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

Neuron 3553 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: 0.2851. Min Range: -0.2851

Max Act: 0.2618. Min Act: -0.0001

Data Index: 554390 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2851. Min Act: -0.0001

Data Index: 48452 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2845. Min Act: -0.0000

Data Index: 582294 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2805. Min Act: -0.0000

Data Index: 265478 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2538. Min Act: -0.0000

Data Index: 646466 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2500. Min Act: -0.0001

Data Index: 461030 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1226990 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2701. Min Act: -0.0001

Data Index: 625445 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2540. Min Act: -0.0001

Data Index: 458884 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2444. Min Act: -0.0001

Data Index: 1292526 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2604. Min Act: -0.0001

Data Index: 683881 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2264. Min Act: -0.0001

Data Index: 1299517 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2377. Min Act: -0.0001

Data Index: 535535 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2210. Min Act: -0.0000

Data Index: 736222 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2543. Min Act: -0.0001

Data Index: 593260 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2301. Min Act: -0.0000

Data Index: 888582 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2272. Min Act: -0.0001

Data Index: 203841 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2327. Min Act: -0.0001

Data Index: 1040583 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2325. Min Act: -0.0001

Data Index: 58873 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2341. Min Act: -0.0001

Data Index: 1322821 (C4 (Web Text))

Max Activating Token Index: 211