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

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

Neuron 4405 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.6067. Min Act: -0.0000

Data Index: 876650 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.8792. Min Act: 0.0000

Data Index: 1154394 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.5816. Min Act: -0.0000

Data Index: 908315 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.3035. Min Act: -0.0000

Data Index: 853859 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.4324. Min Act: -0.0000

Data Index: 897688 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.3588. Min Act: 0.0000

Data Index: 413847 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.2265. Min Act: -0.0000

Data Index: 1118970 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.3860. Min Act: -0.0000

Data Index: 494435 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.1195. Min Act: -0.0000

Data Index: 260530 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.2071. Min Act: -0.0001

Data Index: 745542 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.1895. Min Act: -0.0000

Data Index: 306868 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.1976. Min Act: 0.0000

Data Index: 869664 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.1826. Min Act: -0.0001

Data Index: 150696 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.0916. Min Act: -0.0000

Data Index: 391794 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.2644. Min Act: -0.0000

Data Index: 507960 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.1576. Min Act: -0.0001

Data Index: 622515 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.0309. Min Act: -0.0001

Data Index: 348939 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.0344. Min Act: -0.0000

Data Index: 561954 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.1136. Min Act: -0.0000

Data Index: 102894 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.2270. Min Act: -0.0000

Data Index: 352304 (C4 (Web Text))

Max Activating Token Index: 310