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

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

Neuron 409 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.4891. Min Act: -0.0000

Data Index: 180604 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.4348. Min Act: -0.0000

Data Index: 165900 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3949. Min Act: -0.0000

Data Index: 1523715 (Python Code)

Max Activating Token Index: 348

Text #3

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3697. Min Act: -0.0000

Data Index: 590469 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1335375 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3553. Min Act: -0.0000

Data Index: 732196 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3287. Min Act: -0.0000

Data Index: 115 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3440. Min Act: -0.0000

Data Index: 548695 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3302. Min Act: -0.0000

Data Index: 749384 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1164342 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3375. Min Act: -0.0000

Data Index: 45690 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3238. Min Act: -0.0000

Data Index: 314921 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3209. Min Act: -0.0000

Data Index: 189018 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1353587 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1039777 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3216. Min Act: -0.0000

Data Index: 410501 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3406. Min Act: -0.0000

Data Index: 987806 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3094. Min Act: -0.0000

Data Index: 1174613 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3109. Min Act: -0.0000

Data Index: 844384 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.4891. Min Range: -0.4891

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1106690 (C4 (Web Text))

Max Activating Token Index: 792