Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3292 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.8442. Min Act: -0.0000

Data Index: 60032 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.6074. Min Act: -0.0000

Data Index: 396505 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1062396 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.4928. Min Act: -0.0000

Data Index: 447949 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.4745. Min Act: -0.0000

Data Index: 74835 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1426947 (Python Code)

Max Activating Token Index: 660

Text #6

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1281828 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.4297. Min Act: -0.0000

Data Index: 576211 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1037072 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.3890. Min Act: -0.0000

Data Index: 272094 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.3865. Min Act: -0.0000

Data Index: 873587 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1556407 (Python Code)

Max Activating Token Index: 800

Text #12

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1209332 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.4035. Min Act: -0.0000

Data Index: 582534 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1112490 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.3972. Min Act: -0.0000

Data Index: 515059 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.3594. Min Act: -0.0000

Data Index: 281226 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.3411. Min Act: -0.0000

Data Index: 486021 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.3039. Min Act: -0.0000

Data Index: 71628 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.8442. Min Range: -0.8442

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1475371 (Python Code)

Max Activating Token Index: 146