Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2614 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3466. Min Range: -1.3466

Max Act: 1.3466. Min Act: -0.0000

Data Index: 1228508 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 1.3466. Min Range: -1.3466

Max Act: 1.3171. Min Act: -0.0000

Data Index: 661447 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 1.3466. Min Range: -1.3466

Max Act: 1.1725. Min Act: -0.0000

Data Index: 87697 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 1.3466. Min Range: -1.3466

Max Act: 1.2555. Min Act: -0.0000

Data Index: 721225 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.9577. Min Act: -0.0000

Data Index: 775311 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 1.3466. Min Range: -1.3466

Max Act: 1.0815. Min Act: -0.0000

Data Index: 1200401 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 1.3466. Min Range: -1.3466

Max Act: 1.1077. Min Act: -0.0000

Data Index: 806173 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 1.3466. Min Range: -1.3466

Max Act: 1.1012. Min Act: -0.0000

Data Index: 659484 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 1.3466. Min Range: -1.3466

Max Act: 1.0604. Min Act: -0.0000

Data Index: 1071390 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.9939. Min Act: -0.0000

Data Index: 685161 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1317111 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.8190. Min Act: -0.0000

Data Index: 151809 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1535300 (Python Code)

Max Activating Token Index: 624

Text #13

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.8200. Min Act: -0.0000

Data Index: 638657 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1083857 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.7620. Min Act: -0.0000

Data Index: 346715 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1531687 (Python Code)

Max Activating Token Index: 919

Text #17

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1542534 (Python Code)

Max Activating Token Index: 399

Text #18

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1123396 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.6926. Min Act: -0.0000

Data Index: 481532 (C4 (Web Text))

Max Activating Token Index: 287