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

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

Neuron 5058 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5776. Min Range: -4.5776

Max Act: 4.5776. Min Act: -0.0000

Data Index: 1080357 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 4.5776. Min Range: -4.5776

Max Act: 4.5718. Min Act: -0.0000

Data Index: 611421 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 4.5776. Min Range: -4.5776

Max Act: 4.5343. Min Act: -0.0000

Data Index: 219921 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 4.5776. Min Range: -4.5776

Max Act: 3.9961. Min Act: -0.0000

Data Index: 993931 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 4.5776. Min Range: -4.5776

Max Act: 4.1367. Min Act: -0.0000

Data Index: 769476 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 4.5776. Min Range: -4.5776

Max Act: 4.0388. Min Act: -0.0000

Data Index: 321981 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 4.5776. Min Range: -4.5776

Max Act: 4.0409. Min Act: -0.0000

Data Index: 30247 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 4.5776. Min Range: -4.5776

Max Act: 3.9835. Min Act: -0.0000

Data Index: 979046 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 4.5776. Min Range: -4.5776

Max Act: 3.9352. Min Act: -0.0000

Data Index: 892441 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 4.5776. Min Range: -4.5776

Max Act: 3.5048. Min Act: -0.0000

Data Index: 1334929 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 4.5776. Min Range: -4.5776

Max Act: 3.8443. Min Act: -0.0000

Data Index: 514399 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 4.5776. Min Range: -4.5776

Max Act: 3.7759. Min Act: -0.0000

Data Index: 1352963 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 4.5776. Min Range: -4.5776

Max Act: 3.6484. Min Act: -0.0000

Data Index: 14095 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 4.5776. Min Range: -4.5776

Max Act: 3.6464. Min Act: -0.0000

Data Index: 151087 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 4.5776. Min Range: -4.5776

Max Act: 3.7869. Min Act: -0.0000

Data Index: 1285243 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 4.5776. Min Range: -4.5776

Max Act: 3.6057. Min Act: -0.0000

Data Index: 1152583 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 4.5776. Min Range: -4.5776

Max Act: 3.4326. Min Act: -0.0000

Data Index: 364344 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 4.5776. Min Range: -4.5776

Max Act: 3.4558. Min Act: -0.0000

Data Index: 1082707 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 4.5776. Min Range: -4.5776

Max Act: 3.2604. Min Act: -0.0000

Data Index: 1086496 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 4.5776. Min Range: -4.5776

Max Act: 3.3789. Min Act: -0.0000

Data Index: 711386 (C4 (Web Text))

Max Activating Token Index: 418