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

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

Neuron 5385 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: 2.3158. Min Range: -2.3158

Max Act: 2.3158. Min Act: -0.0000

Data Index: 876805 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 2.3158. Min Range: -2.3158

Max Act: 2.1642. Min Act: -0.0000

Data Index: 677519 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 2.3158. Min Range: -2.3158

Max Act: 2.1026. Min Act: -0.0000

Data Index: 75518 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.8302. Min Act: -0.0000

Data Index: 67110 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.8951. Min Act: -0.0000

Data Index: 388432 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.9145. Min Act: -0.0000

Data Index: 383881 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.6793. Min Act: -0.0000

Data Index: 120527 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.6268. Min Act: -0.0000

Data Index: 1199505 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.5355. Min Act: -0.0000

Data Index: 593321 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.4576. Min Act: -0.0000

Data Index: 1141099 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.4341. Min Act: -0.0000

Data Index: 1095303 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.3349. Min Act: -0.0000

Data Index: 1507921 (Python Code)

Max Activating Token Index: 264

Text #12

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.4807. Min Act: -0.0000

Data Index: 761447 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.3700. Min Act: -0.0000

Data Index: 1085714 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.3317. Min Act: -0.0000

Data Index: 373968 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.3004. Min Act: -0.0000

Data Index: 1420215 (Python Code)

Max Activating Token Index: 445

Text #16

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.2378. Min Act: -0.0000

Data Index: 1554876 (Python Code)

Max Activating Token Index: 1014

Text #17

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.3737. Min Act: -0.0000

Data Index: 287632 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.2874. Min Act: -0.0000

Data Index: 1022901 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 2.3158. Min Range: -2.3158

Max Act: 1.2756. Min Act: -0.0000

Data Index: 26737 (C4 (Web Text))

Max Activating Token Index: 958