Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4222 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.7298. Min Act: -0.0003

Data Index: 235085 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.6618. Min Act: -0.0003

Data Index: 1208716 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.6345. Min Act: -0.0002

Data Index: 630034 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.6399. Min Act: -0.0003

Data Index: 407183 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.6351. Min Act: -0.0003

Data Index: 1297697 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.6371. Min Act: -0.0003

Data Index: 574134 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5063. Min Act: -0.0003

Data Index: 36213 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5660. Min Act: -0.0003

Data Index: 403738 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5509. Min Act: -0.0003

Data Index: 451932 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.4907. Min Act: -0.0003

Data Index: 621416 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5754. Min Act: -0.0003

Data Index: 785172 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.4614. Min Act: -0.0003

Data Index: 959774 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5501. Min Act: -0.0003

Data Index: 1077946 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5866. Min Act: -0.0003

Data Index: 478081 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5671. Min Act: -0.0003

Data Index: 270916 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5311. Min Act: -0.0003

Data Index: 766341 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5084. Min Act: -0.0003

Data Index: 167916 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.4859. Min Act: -0.0003

Data Index: 888129 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.4838. Min Act: -0.0003

Data Index: 287120 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5350. Min Act: -0.0003

Data Index: 987552 (C4 (Web Text))

Max Activating Token Index: 323