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

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

Neuron 834 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.8126. Min Act: -0.0000

Data Index: 840289 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.6674. Min Act: -0.0000

Data Index: 376863 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1184269 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.6044. Min Act: -0.0000

Data Index: 517991 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.4959. Min Act: -0.0000

Data Index: 871922 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.3822. Min Act: -0.0000

Data Index: 636954 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.4025. Min Act: -0.0000

Data Index: 328637 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1202801 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.3875. Min Act: -0.0000

Data Index: 598367 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.3714. Min Act: -0.0000

Data Index: 974358 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.3440. Min Act: -0.0000

Data Index: 24954 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.3463. Min Act: -0.0000

Data Index: 11145 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.3437. Min Act: -0.0000

Data Index: 438772 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1073177 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1302595 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.3605. Min Act: -0.0000

Data Index: 770769 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1052915 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1185003 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.3025. Min Act: -0.0000

Data Index: 299280 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.3222. Min Act: -0.0000

Data Index: 145901 (C4 (Web Text))

Max Activating Token Index: 652