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

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

Neuron 2864 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: 2.6024. Min Range: -2.6024

Max Act: 2.6024. Min Act: -0.0000

Data Index: 242848 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 2.6024. Min Range: -2.6024

Max Act: 2.4041. Min Act: -0.0000

Data Index: 379957 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 2.6024. Min Range: -2.6024

Max Act: 2.4756. Min Act: -0.0000

Data Index: 956057 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 2.6024. Min Range: -2.6024

Max Act: 2.3590. Min Act: -0.0000

Data Index: 1299962 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 2.6024. Min Range: -2.6024

Max Act: 2.2482. Min Act: -0.0000

Data Index: 1326969 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 2.6024. Min Range: -2.6024

Max Act: 2.3320. Min Act: -0.0000

Data Index: 1164891 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 2.6024. Min Range: -2.6024

Max Act: 2.1412. Min Act: -0.0000

Data Index: 1158121 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 2.6024. Min Range: -2.6024

Max Act: 1.9081. Min Act: -0.0000

Data Index: 636125 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 2.6024. Min Range: -2.6024

Max Act: 1.9615. Min Act: -0.0000

Data Index: 523264 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 2.6024. Min Range: -2.6024

Max Act: 1.9052. Min Act: -0.0000

Data Index: 628528 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 2.6024. Min Range: -2.6024

Max Act: 1.7865. Min Act: -0.0000

Data Index: 446149 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 2.6024. Min Range: -2.6024

Max Act: 1.7392. Min Act: -0.0000

Data Index: 687375 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 2.6024. Min Range: -2.6024

Max Act: 1.8364. Min Act: -0.0000

Data Index: 307528 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 2.6024. Min Range: -2.6024

Max Act: 1.7319. Min Act: -0.0000

Data Index: 1200301 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 2.6024. Min Range: -2.6024

Max Act: 1.8244. Min Act: -0.0000

Data Index: 627567 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 2.6024. Min Range: -2.6024

Max Act: 1.7711. Min Act: -0.0000

Data Index: 463576 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 2.6024. Min Range: -2.6024

Max Act: 1.7649. Min Act: -0.0000

Data Index: 873993 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 2.6024. Min Range: -2.6024

Max Act: 1.8344. Min Act: -0.0000

Data Index: 925022 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 2.6024. Min Range: -2.6024

Max Act: 1.6386. Min Act: -0.0000

Data Index: 1350678 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 2.6024. Min Range: -2.6024

Max Act: 1.7030. Min Act: -0.0000

Data Index: 328014 (C4 (Web Text))

Max Activating Token Index: 625