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

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

Neuron 5199 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: 0.5248. Min Range: -0.5248

Max Act: 0.5189. Min Act: -0.0000

Data Index: 636914 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.5248. Min Act: -0.0000

Data Index: 750559 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4691. Min Act: -0.0000

Data Index: 818093 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1302792 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4263. Min Act: -0.0000

Data Index: 321789 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4156. Min Act: -0.0000

Data Index: 570644 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4242. Min Act: -0.0000

Data Index: 375533 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4370. Min Act: -0.0000

Data Index: 60409 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4088. Min Act: -0.0000

Data Index: 330271 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3532. Min Act: -0.0000

Data Index: 631069 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3934. Min Act: -0.0000

Data Index: 899012 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1064333 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3719. Min Act: -0.0000

Data Index: 682336 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3821. Min Act: -0.0000

Data Index: 594286 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3964. Min Act: -0.0000

Data Index: 829266 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3587. Min Act: -0.0000

Data Index: 74359 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1265800 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3607. Min Act: -0.0000

Data Index: 1134348 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3672. Min Act: -0.0000

Data Index: 478945 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3532. Min Act: -0.0000

Data Index: 254658 (C4 (Web Text))

Max Activating Token Index: 508