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

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

Neuron 2617 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: 0.6891. Min Range: -0.6891

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1043394 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1263597 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5584. Min Act: -0.0000

Data Index: 589441 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1003418 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1102215 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5396. Min Act: -0.0001

Data Index: 1192119 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5102. Min Act: -0.0000

Data Index: 463709 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5257. Min Act: -0.0000

Data Index: 478310 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1359088 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5162. Min Act: -0.0001

Data Index: 1072712 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4695. Min Act: -0.0000

Data Index: 782249 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4548. Min Act: -0.0001

Data Index: 946104 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4794. Min Act: -0.0001

Data Index: 17179 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4672. Min Act: -0.0000

Data Index: 40529 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4629. Min Act: -0.0001

Data Index: 935358 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1195027 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4746. Min Act: -0.0000

Data Index: 840430 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1197114 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4260. Min Act: -0.0000

Data Index: 45232 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4339. Min Act: -0.0000

Data Index: 191645 (C4 (Web Text))

Max Activating Token Index: 226