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

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

Neuron 1529 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: 2.9567. Min Range: -2.9567

Max Act: 2.9367. Min Act: -0.0001

Data Index: 143595 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.7393. Min Act: -0.0000

Data Index: 1164973 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.7090. Min Act: -0.0000

Data Index: 1047320 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.9567. Min Act: -0.0001

Data Index: 16972 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.5854. Min Act: -0.0000

Data Index: 442968 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.9110. Min Act: -0.0000

Data Index: 192799 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.6814. Min Act: -0.0000

Data Index: 765570 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.9295. Min Act: -0.0000

Data Index: 492069 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.6542. Min Act: -0.0000

Data Index: 1158237 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.3681. Min Act: -0.0001

Data Index: 432916 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.6247. Min Act: -0.0000

Data Index: 324318 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.6258. Min Act: -0.0000

Data Index: 172012 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.5953. Min Act: -0.0000

Data Index: 842045 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.6423. Min Act: -0.0000

Data Index: 209999 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.2443. Min Act: -0.0000

Data Index: 301033 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.2072. Min Act: -0.0000

Data Index: 209673 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.1313. Min Act: -0.0000

Data Index: 1312981 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.3439. Min Act: -0.0000

Data Index: 1211920 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.2997. Min Act: -0.0001

Data Index: 672314 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 2.9567. Min Range: -2.9567

Max Act: 2.2890. Min Act: -0.0000

Data Index: 936213 (C4 (Web Text))

Max Activating Token Index: 141