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

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

Neuron 1987 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0767. Min Act: -0.0000

Data Index: 583585 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0481. Min Act: -0.0000

Data Index: 559923 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1061569 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0352. Min Act: -0.0000

Data Index: 384825 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0459. Min Act: -0.0000

Data Index: 695451 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0390. Min Act: -0.0000

Data Index: 554164 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1521900 (Python Code)

Max Activating Token Index: 564

Text #7

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0384. Min Act: -0.0000

Data Index: 703502 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0397. Min Act: -0.0000

Data Index: 1639665 (Python Code)

Max Activating Token Index: 316

Text #9

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0433. Min Act: -0.0000

Data Index: 503974 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0344. Min Act: -0.0000

Data Index: 203592 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0374. Min Act: -0.0001

Data Index: 913999 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0406. Min Act: -0.0000

Data Index: 698927 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0341. Min Act: -0.0000

Data Index: 1560706 (Python Code)

Max Activating Token Index: 619

Text #14

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0270. Min Act: -0.0000

Data Index: 1503022 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0302. Min Act: -0.0000

Data Index: 630863 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1086003 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0324. Min Act: -0.0000

Data Index: 242984 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1088166 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1146788 (C4 (Web Text))

Max Activating Token Index: 325