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

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

Neuron 2409 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: 4.5261. Min Range: -4.5261

Max Act: 4.5261. Min Act: -0.0000

Data Index: 454889 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 4.5261. Min Range: -4.5261

Max Act: 4.4440. Min Act: -0.0000

Data Index: 137783 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.9323. Min Act: -0.0000

Data Index: 443921 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.8939. Min Act: -0.0000

Data Index: 1341683 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.6731. Min Act: -0.0000

Data Index: 29001 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.6054. Min Act: -0.0000

Data Index: 369692 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.8913. Min Act: -0.0000

Data Index: 299966 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.7059. Min Act: -0.0000

Data Index: 110308 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.3770. Min Act: -0.0000

Data Index: 854895 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.4026. Min Act: -0.0000

Data Index: 1151033 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.5133. Min Act: -0.0000

Data Index: 1192383 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.3476. Min Act: -0.0000

Data Index: 835862 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.5846. Min Act: -0.0000

Data Index: 1164979 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.2707. Min Act: -0.0000

Data Index: 517132 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.0816. Min Act: -0.0000

Data Index: 694209 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.5166. Min Act: -0.0000

Data Index: 744305 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.6629. Min Act: -0.0000

Data Index: 1273621 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.3291. Min Act: -0.0000

Data Index: 532442 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.2777. Min Act: -0.0000

Data Index: 38123 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 4.5261. Min Range: -4.5261

Max Act: 3.0781. Min Act: -0.0000

Data Index: 1323063 (C4 (Web Text))

Max Activating Token Index: 759