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

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

Neuron 5004 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.3999. Min Act: -0.0000

Data Index: 504083 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.3323. Min Act: -0.0000

Data Index: 783378 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.2130. Min Act: -0.0000

Data Index: 668826 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.1742. Min Act: -0.0000

Data Index: 1334548 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.0784. Min Act: -0.0000

Data Index: 801799 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.1330. Min Act: -0.0000

Data Index: 403945 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.0735. Min Act: -0.0000

Data Index: 368555 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.1287. Min Act: -0.0000

Data Index: 772802 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 1.3999. Min Range: -1.3999

Max Act: 0.9863. Min Act: -0.0000

Data Index: 324790 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.0745. Min Act: -0.0000

Data Index: 164889 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.1343. Min Act: -0.0000

Data Index: 1078031 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 1.3999. Min Range: -1.3999

Max Act: 0.9675. Min Act: -0.0000

Data Index: 582315 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.0320. Min Act: -0.0000

Data Index: 90532 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.0533. Min Act: -0.0000

Data Index: 564490 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.0477. Min Act: -0.0000

Data Index: 899823 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.0286. Min Act: -0.0000

Data Index: 1175603 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.0196. Min Act: -0.0000

Data Index: 599955 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 1.3999. Min Range: -1.3999

Max Act: 0.9807. Min Act: -0.0000

Data Index: 117440 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.3999. Min Range: -1.3999

Max Act: 1.0035. Min Act: -0.0000

Data Index: 475822 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 1.3999. Min Range: -1.3999

Max Act: 0.9127. Min Act: -0.0000

Data Index: 817772 (C4 (Web Text))

Max Activating Token Index: 80