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

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

Neuron 127 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.2908. Min Act: -0.0000

Data Index: 272365 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.2691. Min Act: -0.0000

Data Index: 126822 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.2516. Min Act: -0.0000

Data Index: 589021 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1382. Min Act: -0.0000

Data Index: 94038 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1387. Min Act: -0.0000

Data Index: 696108 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.2208. Min Act: -0.0000

Data Index: 519519 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1527. Min Act: -0.0000

Data Index: 1241092 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1703. Min Act: -0.0000

Data Index: 355127 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0873. Min Act: -0.0000

Data Index: 250386 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1026. Min Act: -0.0000

Data Index: 154808 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0947. Min Act: -0.0000

Data Index: 237695 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1052. Min Act: -0.0000

Data Index: 1219261 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1384. Min Act: -0.0000

Data Index: 259481 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1181. Min Act: -0.0000

Data Index: 1322202 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0352. Min Act: -0.0000

Data Index: 287376 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0280. Min Act: -0.0000

Data Index: 501942 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 1.2908. Min Range: -1.2908

Max Act: 0.9989. Min Act: -0.0000

Data Index: 611706 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0751. Min Act: -0.0000

Data Index: 1168727 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0880. Min Act: -0.0000

Data Index: 164601 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 1.2908. Min Range: -1.2908

Max Act: 0.9933. Min Act: -0.0000

Data Index: 1043005 (C4 (Web Text))

Max Activating Token Index: 87