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

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

Neuron 5631 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: 1.4382. Min Range: -1.4382

Max Act: 1.3488. Min Act: -0.0000

Data Index: 339793 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.4382. Min Act: -0.0000

Data Index: 1515872 (Python Code)

Max Activating Token Index: 926

Text #2

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2554. Min Act: -0.0000

Data Index: 1613114 (Python Code)

Max Activating Token Index: 961

Text #3

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.4039. Min Act: -0.0000

Data Index: 1251026 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2652. Min Act: -0.0000

Data Index: 1637765 (Python Code)

Max Activating Token Index: 569

Text #5

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1585828 (Python Code)

Max Activating Token Index: 258

Text #6

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.3256. Min Act: -0.0000

Data Index: 1538092 (Python Code)

Max Activating Token Index: 135

Text #7

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.3269. Min Act: -0.0000

Data Index: 1623925 (Python Code)

Max Activating Token Index: 611

Text #8

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.1617. Min Act: -0.0000

Data Index: 1483642 (Python Code)

Max Activating Token Index: 784

Text #9

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.3199. Min Act: -0.0000

Data Index: 1404065 (Python Code)

Max Activating Token Index: 169

Text #10

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.3650. Min Act: -0.0000

Data Index: 1507744 (Python Code)

Max Activating Token Index: 845

Text #11

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0939. Min Act: -0.0000

Data Index: 364143 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.1602. Min Act: -0.0000

Data Index: 1542946 (Python Code)

Max Activating Token Index: 752

Text #13

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2223. Min Act: -0.0000

Data Index: 1634183 (Python Code)

Max Activating Token Index: 721

Text #14

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.1296. Min Act: -0.0000

Data Index: 1467849 (Python Code)

Max Activating Token Index: 948

Text #15

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0690. Min Act: -0.0000

Data Index: 1382967 (Python Code)

Max Activating Token Index: 929

Text #16

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1469259 (Python Code)

Max Activating Token Index: 965

Text #17

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.1124. Min Act: -0.0000

Data Index: 1458209 (Python Code)

Max Activating Token Index: 250

Text #18

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0761. Min Act: -0.0000

Data Index: 1588571 (Python Code)

Max Activating Token Index: 736

Text #19

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1636234 (Python Code)

Max Activating Token Index: 102