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

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

Neuron 6115 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1537239 (Python Code)

Max Activating Token Index: 139

Text #1

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1105714 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1628225 (Python Code)

Max Activating Token Index: 222

Text #3

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3792. Min Act: 0.0000

Data Index: 1441982 (Python Code)

Max Activating Token Index: 642

Text #4

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3806. Min Act: -0.0000

Data Index: 396984 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3622. Min Act: -0.0000

Data Index: 572895 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3468. Min Act: -0.0000

Data Index: 633237 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3391. Min Act: -0.0000

Data Index: 594371 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3070. Min Act: -0.0000

Data Index: 239248 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3156. Min Act: -0.0000

Data Index: 815773 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1303946 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1354685 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1295775 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3073. Min Act: -0.0000

Data Index: 138661 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1359285 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3148. Min Act: -0.0000

Data Index: 850716 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1117785 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3022. Min Act: -0.0000

Data Index: 823476 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.2883. Min Act: -0.0000

Data Index: 11521 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.2864. Min Act: -0.0000

Data Index: 37633 (C4 (Web Text))

Max Activating Token Index: 46