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

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

Neuron 4732 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0277. Min Range: -1.0277

Max Act: 1.0024. Min Act: -0.0000

Data Index: 52224 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 1.0277. Min Range: -1.0277

Max Act: 1.0196. Min Act: -0.0000

Data Index: 466880 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 1.0277. Min Range: -1.0277

Max Act: 1.0125. Min Act: -0.0000

Data Index: 492481 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.9839. Min Act: -0.0000

Data Index: 864095 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 1.0277. Min Range: -1.0277

Max Act: 1.0038. Min Act: -0.0000

Data Index: 678674 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 1.0277. Min Range: -1.0277

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1319621 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.8912. Min Act: -0.0000

Data Index: 692503 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.8488. Min Act: -0.0000

Data Index: 666828 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.8900. Min Act: -0.0000

Data Index: 894877 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1367081 (Python Code)

Max Activating Token Index: 265

Text #10

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.8556. Min Act: -0.0000

Data Index: 503830 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1409971 (Python Code)

Max Activating Token Index: 48

Text #12

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.7649. Min Act: -0.0000

Data Index: 809076 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1040486 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1526503 (Python Code)

Max Activating Token Index: 159

Text #15

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1543897 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.6657. Min Act: -0.0000

Data Index: 695804 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.7385. Min Act: -0.0000

Data Index: 1371340 (Python Code)

Max Activating Token Index: 900

Text #18

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1628110 (Python Code)

Max Activating Token Index: 785

Text #19

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.6816. Min Act: -0.0000

Data Index: 748146 (C4 (Web Text))

Max Activating Token Index: 706