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

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

Neuron 5322 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4971. Min Act: -0.0000

Data Index: 979914 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4987. Min Act: -0.0000

Data Index: 746223 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.5020. Min Act: -0.0000

Data Index: 57958 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4502. Min Act: -0.0000

Data Index: 965445 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4542. Min Act: -0.0000

Data Index: 149021 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4196. Min Act: -0.0000

Data Index: 596336 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4248. Min Act: -0.0000

Data Index: 821847 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4333. Min Act: -0.0000

Data Index: 498920 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1213383 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3779. Min Act: -0.0000

Data Index: 247711 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1655123 (Python Code)

Max Activating Token Index: 488

Text #11

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4394. Min Act: -0.0000

Data Index: 513024 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1456862 (Python Code)

Max Activating Token Index: 274

Text #13

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3929. Min Act: -0.0000

Data Index: 774536 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1423417 (Python Code)

Max Activating Token Index: 864

Text #15

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1189644 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1138638 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1017238 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1400086 (Python Code)

Max Activating Token Index: 975

Text #19

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3623. Min Act: -0.0000

Data Index: 389845 (C4 (Web Text))

Max Activating Token Index: 310