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

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

Neuron 3700 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.4208. Min Act: -0.0000

Data Index: 877069 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1037964 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3710. Min Act: -0.0000

Data Index: 893482 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1231103 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3448. Min Act: -0.0000

Data Index: 820288 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1037249 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3376. Min Act: -0.0000

Data Index: 621708 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3279. Min Act: -0.0000

Data Index: 382309 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3249. Min Act: -0.0000

Data Index: 778526 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3317. Min Act: -0.0000

Data Index: 487563 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3203. Min Act: -0.0000

Data Index: 584944 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3148. Min Act: -0.0000

Data Index: 379315 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3053. Min Act: -0.0000

Data Index: 780857 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3149. Min Act: -0.0000

Data Index: 381210 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.2887. Min Act: -0.0000

Data Index: 585786 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.2827. Min Act: -0.0000

Data Index: 92888 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3093. Min Act: 0.0000

Data Index: 1343030 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.2851. Min Act: -0.0000

Data Index: 408896 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.2768. Min Act: -0.0000

Data Index: 449846 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1064950 (C4 (Web Text))

Max Activating Token Index: 706