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

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

Neuron 5403 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: 3.5344. Min Range: -3.5344

Max Act: 3.5344. Min Act: -0.0000

Data Index: 554189 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.9544. Min Act: -0.0001

Data Index: 786219 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.9873. Min Act: -0.0001

Data Index: 1186990 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 3.5344. Min Range: -3.5344

Max Act: 3.0181. Min Act: -0.0001

Data Index: 132902 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 3.5344. Min Range: -3.5344

Max Act: 3.0338. Min Act: -0.0000

Data Index: 354272 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.8295. Min Act: -0.0000

Data Index: 148955 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.7563. Min Act: -0.0001

Data Index: 205786 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.8305. Min Act: -0.0001

Data Index: 346975 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.6488. Min Act: -0.0001

Data Index: 1064354 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.5780. Min Act: -0.0001

Data Index: 884961 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.6893. Min Act: -0.0001

Data Index: 1042499 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.5361. Min Act: -0.0001

Data Index: 1330036 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.5075. Min Act: -0.0001

Data Index: 1048726 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.5100. Min Act: -0.0001

Data Index: 506620 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.5918. Min Act: -0.0001

Data Index: 436722 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.4689. Min Act: -0.0000

Data Index: 639457 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.4155. Min Act: -0.0001

Data Index: 727662 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.4927. Min Act: -0.0000

Data Index: 613511 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.3655. Min Act: -0.0001

Data Index: 819481 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 3.5344. Min Range: -3.5344

Max Act: 2.3207. Min Act: -0.0001

Data Index: 1102807 (C4 (Web Text))

Max Activating Token Index: 292