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

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

Neuron 2004 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: 1.4503. Min Range: -1.4503

Max Act: 1.4503. Min Act: -0.0000

Data Index: 1046042 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.2179. Min Act: -0.0000

Data Index: 68790 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.0744. Min Act: -0.0000

Data Index: 796583 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.1447. Min Act: -0.0000

Data Index: 37053 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 1.4503. Min Range: -1.4503

Max Act: 0.9542. Min Act: -0.0000

Data Index: 691876 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.0341. Min Act: -0.0000

Data Index: 995640 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.0247. Min Act: -0.0000

Data Index: 552783 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 1.4503. Min Range: -1.4503

Max Act: 0.9627. Min Act: -0.0000

Data Index: 1121369 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 1.4503. Min Range: -1.4503

Max Act: 0.9386. Min Act: -0.0000

Data Index: 19965 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 1.4503. Min Range: -1.4503

Max Act: 0.9289. Min Act: -0.0000

Data Index: 593835 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 1.4503. Min Range: -1.4503

Max Act: 0.9815. Min Act: -0.0000

Data Index: 989214 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.0458. Min Act: -0.0000

Data Index: 1638838 (Python Code)

Max Activating Token Index: 38

Text #12

Max Range: 1.4503. Min Range: -1.4503

Max Act: 0.9842. Min Act: -0.0000

Data Index: 641480 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.4503. Min Range: -1.4503

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1029763 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 1.4503. Min Range: -1.4503

Max Act: 0.9626. Min Act: -0.0000

Data Index: 447483 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 1.4503. Min Range: -1.4503

Max Act: 0.8037. Min Act: -0.0000

Data Index: 932832 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 1.4503. Min Range: -1.4503

Max Act: 0.8806. Min Act: -0.0000

Data Index: 1234008 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 1.4503. Min Range: -1.4503

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1035253 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 1.4503. Min Range: -1.4503

Max Act: 0.9362. Min Act: -0.0000

Data Index: 1067848 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 1.4503. Min Range: -1.4503

Max Act: 0.9303. Min Act: -0.0000

Data Index: 775125 (C4 (Web Text))

Max Activating Token Index: 997