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

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

Neuron 1963 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: 0.4351. Min Range: -0.4351

Max Act: 0.4346. Min Act: -0.0000

Data Index: 995448 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4351. Min Act: -0.0000

Data Index: 455144 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1305020 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2968. Min Act: -0.0000

Data Index: 427646 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3019. Min Act: -0.0000

Data Index: 262133 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3106. Min Act: -0.0000

Data Index: 573700 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3434. Min Act: -0.0000

Data Index: 82535 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2756. Min Act: -0.0000

Data Index: 325220 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2842. Min Act: -0.0000

Data Index: 734565 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2839. Min Act: -0.0000

Data Index: 1076088 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1445260 (Python Code)

Max Activating Token Index: 839

Text #11

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1240638 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2310. Min Act: -0.0000

Data Index: 969518 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2655. Min Act: -0.0000

Data Index: 593626 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1537496 (Python Code)

Max Activating Token Index: 718

Text #15

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1252375 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2344. Min Act: -0.0000

Data Index: 192440 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3564. Min Act: -0.0000

Data Index: 554668 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1041273 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2415. Min Act: -0.0000

Data Index: 887752 (C4 (Web Text))

Max Activating Token Index: 692