Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 425 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1549. Min Range: -1.1549

Max Act: 1.1549. Min Act: -0.0001

Data Index: 389430 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 1.1549. Min Range: -1.1549

Max Act: 1.1289. Min Act: -0.0001

Data Index: 817171 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 1.1549. Min Range: -1.1549

Max Act: 1.0264. Min Act: -0.0000

Data Index: 90256 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.9918. Min Act: -0.0001

Data Index: 155331 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 1.1549. Min Range: -1.1549

Max Act: 1.0327. Min Act: -0.0000

Data Index: 741851 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1356283 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.9442. Min Act: -0.0001

Data Index: 833668 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.9662. Min Act: -0.0001

Data Index: 1112519 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1336766 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.9662. Min Act: -0.0001

Data Index: 1146343 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.9695. Min Act: -0.0001

Data Index: 488334 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.9458. Min Act: -0.0001

Data Index: 107206 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.9134. Min Act: -0.0000

Data Index: 11700 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.9063. Min Act: -0.0001

Data Index: 320131 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1322066 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.8929. Min Act: -0.0000

Data Index: 201781 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.8890. Min Act: -0.0001

Data Index: 650139 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.8652. Min Act: -0.0001

Data Index: 177529 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.9201. Min Act: -0.0000

Data Index: 872306 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 1.1549. Min Range: -1.1549

Max Act: 0.8872. Min Act: -0.0000

Data Index: 1077113 (C4 (Web Text))

Max Activating Token Index: 31