Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2180 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.7559. Min Act: -0.0002

Data Index: 1320324 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.6418. Min Act: -0.0001

Data Index: 320626 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.5202. Min Act: -0.0002

Data Index: 987067 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.5014. Min Act: -0.0002

Data Index: 33502 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.4615. Min Act: -0.0002

Data Index: 1006386 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.4990. Min Act: -0.0001

Data Index: 830416 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.3354. Min Act: -0.0001

Data Index: 802380 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.2939. Min Act: -0.0001

Data Index: 601840 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.3233. Min Act: -0.0001

Data Index: 1329390 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.3465. Min Act: -0.0002

Data Index: 66023 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.2635. Min Act: -0.0002

Data Index: 71378 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.2413. Min Act: -0.0001

Data Index: 140624 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.3208. Min Act: -0.0002

Data Index: 1347897 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.1756. Min Act: -0.0002

Data Index: 741974 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.2313. Min Act: -0.0002

Data Index: 8958 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.2586. Min Act: -0.0001

Data Index: 419176 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.2348. Min Act: -0.0002

Data Index: 490659 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.2601. Min Act: -0.0002

Data Index: 463462 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.2383. Min Act: -0.0002

Data Index: 1147715 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.1897. Min Act: -0.0001

Data Index: 981369 (C4 (Web Text))

Max Activating Token Index: 810