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

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

Neuron 5095 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.5845. Min Act: -0.0000

Data Index: 1556432 (Python Code)

Max Activating Token Index: 124

Text #1

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1525422 (Python Code)

Max Activating Token Index: 419

Text #2

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1444. Min Act: -0.0000

Data Index: 1627658 (Python Code)

Max Activating Token Index: 66

Text #3

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.0844. Min Act: -0.0000

Data Index: 1368505 (Python Code)

Max Activating Token Index: 923

Text #4

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1123. Min Act: -0.0000

Data Index: 1604226 (Python Code)

Max Activating Token Index: 148

Text #5

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1318. Min Act: -0.0000

Data Index: 1644969 (Python Code)

Max Activating Token Index: 431

Text #6

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1315. Min Act: -0.0000

Data Index: 1577483 (Python Code)

Max Activating Token Index: 265

Text #7

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1091. Min Act: -0.0000

Data Index: 1598430 (Python Code)

Max Activating Token Index: 270

Text #8

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.0208. Min Act: -0.0000

Data Index: 1404799 (Python Code)

Max Activating Token Index: 70

Text #9

Max Range: 1.5845. Min Range: -1.5845

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1436508 (Python Code)

Max Activating Token Index: 302

Text #10

Max Range: 1.5845. Min Range: -1.5845

Max Act: 0.9948. Min Act: -0.0000

Data Index: 1501898 (Python Code)

Max Activating Token Index: 205

Text #11

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1431422 (Python Code)

Max Activating Token Index: 611

Text #12

Max Range: 1.5845. Min Range: -1.5845

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1451683 (Python Code)

Max Activating Token Index: 86

Text #13

Max Range: 1.5845. Min Range: -1.5845

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1377031 (Python Code)

Max Activating Token Index: 229

Text #14

Max Range: 1.5845. Min Range: -1.5845

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1379534 (Python Code)

Max Activating Token Index: 153

Text #15

Max Range: 1.5845. Min Range: -1.5845

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1457456 (Python Code)

Max Activating Token Index: 239

Text #16

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1469321 (Python Code)

Max Activating Token Index: 684

Text #17

Max Range: 1.5845. Min Range: -1.5845

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1471738 (Python Code)

Max Activating Token Index: 930

Text #18

Max Range: 1.5845. Min Range: -1.5845

Max Act: 0.9432. Min Act: -0.0000

Data Index: 1550013 (Python Code)

Max Activating Token Index: 341

Text #19

Max Range: 1.5845. Min Range: -1.5845

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1579893 (Python Code)

Max Activating Token Index: 700