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

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

Neuron 1577 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: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0000

Data Index: 807281 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0460. Min Act: -0.0000

Data Index: 803925 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1282763 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0400. Min Act: -0.0000

Data Index: 426992 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0411. Min Act: -0.0001

Data Index: 723175 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0389. Min Act: -0.0001

Data Index: 128085 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0377. Min Act: -0.0001

Data Index: 348206 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0375. Min Act: -0.0001

Data Index: 910367 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0398. Min Act: -0.0000

Data Index: 456954 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0388. Min Act: -0.0001

Data Index: 639586 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0387. Min Act: -0.0001

Data Index: 931432 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0370. Min Act: -0.0001

Data Index: 384778 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1439664 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0387. Min Act: -0.0000

Data Index: 569783 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0358. Min Act: -0.0001

Data Index: 1233809 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0371. Min Act: -0.0000

Data Index: 87818 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0364. Min Act: -0.0001

Data Index: 1014221 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0366. Min Act: -0.0001

Data Index: 278962 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0372. Min Act: -0.0000

Data Index: 1220453 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1253169 (C4 (Web Text))

Max Activating Token Index: 378