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

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

Neuron 4997 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0240. Min Range: -2.0240

Max Act: 2.0240. Min Act: -0.0000

Data Index: 647421 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.8316. Min Act: -0.0000

Data Index: 1163036 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.8143. Min Act: -0.0000

Data Index: 731993 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.9015. Min Act: -0.0000

Data Index: 822527 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.8425. Min Act: -0.0000

Data Index: 826600 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.7810. Min Act: -0.0000

Data Index: 137836 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.5886. Min Act: -0.0000

Data Index: 286180 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.5576. Min Act: -0.0000

Data Index: 315002 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.6418. Min Act: -0.0000

Data Index: 335707 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.4017. Min Act: -0.0000

Data Index: 728895 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.5217. Min Act: -0.0000

Data Index: 1169547 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.5822. Min Act: -0.0000

Data Index: 1086013 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.5453. Min Act: -0.0000

Data Index: 431370 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.5479. Min Act: -0.0000

Data Index: 41130 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.5882. Min Act: -0.0000

Data Index: 535807 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.4276. Min Act: -0.0000

Data Index: 528662 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.5978. Min Act: -0.0000

Data Index: 1215824 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.4200. Min Act: -0.0000

Data Index: 860369 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.4882. Min Act: -0.0000

Data Index: 958291 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 2.0240. Min Range: -2.0240

Max Act: 1.4005. Min Act: -0.0000

Data Index: 1242016 (C4 (Web Text))

Max Activating Token Index: 869