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

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

Neuron 3006 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.1243. Min Act: -0.0001

Data Index: 888075 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.0454. Min Act: -0.0000

Data Index: 1211613 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1206946 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.0492. Min Act: -0.0000

Data Index: 529310 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.0388. Min Act: -0.0001

Data Index: 808588 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.0049. Min Act: -0.0001

Data Index: 373665 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.0425. Min Act: -0.0001

Data Index: 725527 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.0128. Min Act: -0.0001

Data Index: 612506 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9807. Min Act: -0.0001

Data Index: 935839 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9097. Min Act: -0.0000

Data Index: 1100594 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9054. Min Act: -0.0001

Data Index: 1011761 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9325. Min Act: -0.0001

Data Index: 211222 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.1044. Min Act: -0.0000

Data Index: 545262 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8516. Min Act: -0.0001

Data Index: 979899 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8453. Min Act: -0.0000

Data Index: 669024 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9343. Min Act: -0.0001

Data Index: 507847 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8124. Min Act: -0.0001

Data Index: 343598 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8957. Min Act: -0.0000

Data Index: 1163515 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8329. Min Act: -0.0000

Data Index: 594020 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1063560 (C4 (Web Text))

Max Activating Token Index: 153