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

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

Neuron 1966 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.4982. Min Act: -0.0000

Data Index: 161046 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.2384. Min Act: -0.0000

Data Index: 10206 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.1286. Min Act: -0.0000

Data Index: 633483 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.2296. Min Act: -0.0000

Data Index: 255360 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.9555. Min Act: -0.0000

Data Index: 567440 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.8989. Min Act: -0.0000

Data Index: 309491 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.8898. Min Act: -0.0000

Data Index: 970773 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.9373. Min Act: -0.0000

Data Index: 358167 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.8616. Min Act: -0.0000

Data Index: 333360 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.8244. Min Act: -0.0000

Data Index: 743393 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.7733. Min Act: -0.0000

Data Index: 466952 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.7698. Min Act: -0.0000

Data Index: 821770 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.7533. Min Act: -0.0000

Data Index: 313291 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.7441. Min Act: -0.0000

Data Index: 443090 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.7285. Min Act: -0.0000

Data Index: 807171 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.7085. Min Act: -0.0000

Data Index: 480648 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.6727. Min Act: -0.0000

Data Index: 82502 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.6506. Min Act: -0.0000

Data Index: 637414 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.6685. Min Act: 0.0001

Data Index: 1229718 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 1.4982. Min Range: -1.4982

Max Act: 0.6674. Min Act: 0.0001

Data Index: 774682 (C4 (Web Text))

Max Activating Token Index: 653