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

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

Neuron 1594 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3162. Min Range: -2.3162

Max Act: 2.3162. Min Act: -0.0000

Data Index: 1129572 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 2.3162. Min Range: -2.3162

Max Act: 2.0686. Min Act: -0.0000

Data Index: 1148910 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.8187. Min Act: -0.0000

Data Index: 1105684 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.8542. Min Act: -0.0000

Data Index: 781637 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.8435. Min Act: -0.0000

Data Index: 1105980 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.8496. Min Act: -0.0000

Data Index: 212010 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.6074. Min Act: -0.0000

Data Index: 972932 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.7950. Min Act: -0.0000

Data Index: 227921 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.6576. Min Act: -0.0000

Data Index: 323002 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.4517. Min Act: -0.0000

Data Index: 242427 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.7297. Min Act: -0.0000

Data Index: 405507 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.6280. Min Act: -0.0000

Data Index: 978975 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.7159. Min Act: -0.0000

Data Index: 427301 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.6110. Min Act: -0.0000

Data Index: 1239409 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.4713. Min Act: -0.0000

Data Index: 693987 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.4643. Min Act: -0.0000

Data Index: 95819 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.5542. Min Act: -0.0000

Data Index: 171476 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.4360. Min Act: -0.0000

Data Index: 1198320 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.6247. Min Act: -0.0000

Data Index: 730925 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 2.3162. Min Range: -2.3162

Max Act: 1.6036. Min Act: -0.0000

Data Index: 359020 (C4 (Web Text))

Max Activating Token Index: 935