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

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

Neuron 4486 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.5057. Min Act: -0.0000

Data Index: 963405 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.4553. Min Act: -0.0000

Data Index: 763861 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.4373. Min Act: -0.0000

Data Index: 172978 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.4380. Min Act: -0.0000

Data Index: 871164 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.4534. Min Act: -0.0000

Data Index: 787763 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1291838 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.4293. Min Act: -0.0000

Data Index: 416378 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.4418. Min Act: -0.0000

Data Index: 209822 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.4249. Min Act: -0.0000

Data Index: 641550 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1050033 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1232810 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.4150. Min Act: -0.0000

Data Index: 217987 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3919. Min Act: -0.0000

Data Index: 451310 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3876. Min Act: -0.0000

Data Index: 432290 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3734. Min Act: -0.0000

Data Index: 107689 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.4061. Min Act: -0.0000

Data Index: 372148 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.4032. Min Act: -0.0000

Data Index: 379041 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3952. Min Act: -0.0000

Data Index: 884947 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.3673. Min Act: -0.0000

Data Index: 480492 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.5057. Min Range: -0.5057

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1236154 (C4 (Web Text))

Max Activating Token Index: 96