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

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

Neuron 1406 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.4549. Min Act: -0.0000

Data Index: 1105734 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.2249. Min Act: -0.0000

Data Index: 1258703 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.1659. Min Act: -0.0000

Data Index: 341977 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.0664. Min Act: -0.0000

Data Index: 897164 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.0678. Min Act: -0.0000

Data Index: 1166550 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.0984. Min Act: -0.0000

Data Index: 46142 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.0187. Min Act: -0.0000

Data Index: 1241035 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.2008. Min Act: -0.0000

Data Index: 123947 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.1263. Min Act: -0.0000

Data Index: 118978 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.0388. Min Act: -0.0000

Data Index: 943802 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.0329. Min Act: -0.0000

Data Index: 1061841 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.0891. Min Act: -0.0000

Data Index: 994292 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.0011. Min Act: -0.0000

Data Index: 15742 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.0533. Min Act: -0.0000

Data Index: 562206 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.9564. Min Act: -0.0000

Data Index: 704951 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.9830. Min Act: -0.0000

Data Index: 103019 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 1.4549. Min Range: -1.4549

Max Act: 1.0077. Min Act: -0.0000

Data Index: 878214 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.9994. Min Act: -0.0000

Data Index: 1087224 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.9673. Min Act: -0.0000

Data Index: 182271 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 1.4549. Min Range: -1.4549

Max Act: 0.9518. Min Act: -0.0000

Data Index: 980857 (C4 (Web Text))

Max Activating Token Index: 577