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

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

Neuron 4068 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: 0.9755. Min Range: -0.9755

Max Act: 0.9448. Min Act: -0.0000

Data Index: 982225 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.9755. Min Act: -0.0000

Data Index: 1200087 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.8723. Min Act: -0.0000

Data Index: 811297 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.8710. Min Act: -0.0001

Data Index: 326420 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.8380. Min Act: -0.0001

Data Index: 35391 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1167913 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7537. Min Act: -0.0000

Data Index: 805583 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7495. Min Act: -0.0001

Data Index: 918508 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7642. Min Act: -0.0001

Data Index: 937311 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7320. Min Act: -0.0000

Data Index: 730282 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7191. Min Act: -0.0000

Data Index: 451595 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7108. Min Act: -0.0001

Data Index: 860742 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6851. Min Act: -0.0001

Data Index: 214090 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6447. Min Act: -0.0001

Data Index: 404897 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6477. Min Act: -0.0000

Data Index: 874531 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6181. Min Act: -0.0001

Data Index: 1546385 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6464. Min Act: -0.0000

Data Index: 345154 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6041. Min Act: -0.0000

Data Index: 332185 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6401. Min Act: -0.0000

Data Index: 804377 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6348. Min Act: -0.0000

Data Index: 539818 (C4 (Web Text))

Max Activating Token Index: 163