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

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

Neuron 3398 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3230. Min Range: -3.3230

Max Act: 3.3230. Min Act: -0.0001

Data Index: 711265 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.9988. Min Act: -0.0001

Data Index: 470525 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.7972. Min Act: -0.0001

Data Index: 996501 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.8367. Min Act: -0.0001

Data Index: 655723 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.7351. Min Act: -0.0000

Data Index: 577326 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.6780. Min Act: -0.0001

Data Index: 762375 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.6934. Min Act: -0.0001

Data Index: 21183 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.4219. Min Act: -0.0001

Data Index: 865338 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.7582. Min Act: -0.0000

Data Index: 107305 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.5569. Min Act: -0.0001

Data Index: 883158 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.3141. Min Act: -0.0001

Data Index: 644032 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.4272. Min Act: -0.0001

Data Index: 575076 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.5523. Min Act: -0.0001

Data Index: 1358836 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.1082. Min Act: -0.0001

Data Index: 1169725 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.2946. Min Act: -0.0001

Data Index: 672882 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.4145. Min Act: -0.0001

Data Index: 475649 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.0839. Min Act: -0.0001

Data Index: 1338274 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.5163. Min Act: -0.0001

Data Index: 83691 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 3.3230. Min Range: -3.3230

Max Act: 2.3961. Min Act: -0.0001

Data Index: 1337215 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 3.3230. Min Range: -3.3230

Max Act: 1.8864. Min Act: -0.0001

Data Index: 859586 (C4 (Web Text))

Max Activating Token Index: 312