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

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

Neuron 473 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2932. Min Range: -2.2932

Max Act: 2.2932. Min Act: -0.0000

Data Index: 533419 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1556150 (Python Code)

Max Activating Token Index: 372

Text #2

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1635814 (Python Code)

Max Activating Token Index: 672

Text #3

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.4720. Min Act: -0.0000

Data Index: 708878 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1488111 (Python Code)

Max Activating Token Index: 367

Text #5

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.4324. Min Act: -0.0000

Data Index: 56456 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1640244 (Python Code)

Max Activating Token Index: 527

Text #7

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.4088. Min Act: -0.0000

Data Index: 958968 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.4216. Min Act: -0.0000

Data Index: 530265 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.3994. Min Act: -0.0000

Data Index: 374633 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.4221. Min Act: -0.0000

Data Index: 284508 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.4065. Min Act: -0.0000

Data Index: 869837 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1447537 (Python Code)

Max Activating Token Index: 906

Text #13

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1140547 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1111400 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.3878. Min Act: -0.0000

Data Index: 600084 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.3675. Min Act: -0.0000

Data Index: 1298177 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.3529. Min Act: -0.0000

Data Index: 444279 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1219458 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 2.2932. Min Range: -2.2932

Max Act: 0.3775. Min Act: -0.0000

Data Index: 995026 (C4 (Web Text))

Max Activating Token Index: 708