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

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

Neuron 5753 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6840. Min Act: -0.0000

Data Index: 1570549 (Python Code)

Max Activating Token Index: 765

Text #1

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1379839 (Python Code)

Max Activating Token Index: 382

Text #2

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6375. Min Act: -0.0000

Data Index: 969501 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6326. Min Act: -0.0000

Data Index: 764714 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1458419 (Python Code)

Max Activating Token Index: 729

Text #5

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1548776 (Python Code)

Max Activating Token Index: 624

Text #6

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1447320 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1542745 (Python Code)

Max Activating Token Index: 835

Text #8

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5981. Min Act: 0.0000

Data Index: 121769 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.4943. Min Act: -0.0000

Data Index: 214371 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5245. Min Act: -0.0000

Data Index: 621419 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1330870 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.4208. Min Act: -0.0000

Data Index: 260559 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1292973 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.4957. Min Act: -0.0000

Data Index: 512850 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1213677 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5015. Min Act: -0.0000

Data Index: 133845 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.4643. Min Act: -0.0000

Data Index: 594439 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1300142 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1340282 (C4 (Web Text))

Max Activating Token Index: 150