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

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

Neuron 3196 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: 1.0400. Min Range: -1.0400

Max Act: 1.0400. Min Act: 0.0002

Data Index: 750498 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7972. Min Act: -0.0000

Data Index: 554655 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1307019 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.6399. Min Act: -0.0000

Data Index: 588343 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.6742. Min Act: -0.0000

Data Index: 79481 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1083987 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1090350 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.5803. Min Act: 0.0001

Data Index: 316042 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.6026. Min Act: -0.0000

Data Index: 501513 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1265084 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.6333. Min Act: -0.0000

Data Index: 481845 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.5614. Min Act: -0.0000

Data Index: 820659 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.5661. Min Act: 0.0000

Data Index: 1277261 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.5669. Min Act: -0.0000

Data Index: 710401 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.5623. Min Act: -0.0000

Data Index: 284820 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.5258. Min Act: -0.0000

Data Index: 142428 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1273474 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1065360 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.5282. Min Act: -0.0000

Data Index: 248279 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.5436. Min Act: -0.0000

Data Index: 248311 (C4 (Web Text))

Max Activating Token Index: 390