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

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

Neuron 3414 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3781. Min Act: -0.0001

Data Index: 641319 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3605. Min Act: -0.0001

Data Index: 808372 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3547. Min Act: -0.0001

Data Index: 1241475 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3472. Min Act: -0.0001

Data Index: 790514 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3383. Min Act: -0.0001

Data Index: 799362 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3414. Min Act: -0.0001

Data Index: 1065215 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3419. Min Act: -0.0001

Data Index: 1167648 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3422. Min Act: -0.0001

Data Index: 657101 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3375. Min Act: -0.0001

Data Index: 64496 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3155. Min Act: -0.0001

Data Index: 921957 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3326. Min Act: -0.0001

Data Index: 1235548 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3214. Min Act: -0.0001

Data Index: 635258 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3307. Min Act: -0.0001

Data Index: 920784 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3284. Min Act: -0.0001

Data Index: 580079 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3269. Min Act: -0.0001

Data Index: 743100 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3338. Min Act: -0.0001

Data Index: 727995 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3240. Min Act: -0.0001

Data Index: 951554 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3229. Min Act: -0.0001

Data Index: 1242639 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3056. Min Act: -0.0001

Data Index: 1283805 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3067. Min Act: -0.0001

Data Index: 819981 (C4 (Web Text))

Max Activating Token Index: 41