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

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

Neuron 2911 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.7763. Min Act: -0.0000

Data Index: 1182362 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.9243. Min Act: -0.0000

Data Index: 663899 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8714. Min Act: -0.0000

Data Index: 949811 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.7281. Min Act: -0.0000

Data Index: 274125 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8603. Min Act: -0.0000

Data Index: 384885 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.9178. Min Act: -0.0000

Data Index: 664885 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.7636. Min Act: -0.0000

Data Index: 1001597 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8909. Min Act: -0.0000

Data Index: 865589 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.7253. Min Act: -0.0000

Data Index: 742388 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.5473. Min Act: -0.0000

Data Index: 555772 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.5392. Min Act: -0.0000

Data Index: 926387 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.4673. Min Act: -0.0000

Data Index: 729138 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.4828. Min Act: -0.0000

Data Index: 450352 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.1586. Min Act: -0.0000

Data Index: 1134581 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.4270. Min Act: -0.0000

Data Index: 105724 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.2968. Min Act: -0.0000

Data Index: 1337233 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.3996. Min Act: -0.0000

Data Index: 1233321 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.2778. Min Act: -0.0000

Data Index: 12588 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.2150. Min Act: -0.0000

Data Index: 197240 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.0162. Min Act: -0.0000

Data Index: 1316819 (C4 (Web Text))

Max Activating Token Index: 266