Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1357 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.5127. Min Act: -0.0001

Data Index: 1500447 (Python Code)

Max Activating Token Index: 421

Text #1

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.4185. Min Act: -0.0000

Data Index: 1617309 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.4403. Min Act: -0.0001

Data Index: 1515680 (Python Code)

Max Activating Token Index: 423

Text #3

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1469109 (Python Code)

Max Activating Token Index: 351

Text #4

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.4157. Min Act: -0.0000

Data Index: 1476720 (Python Code)

Max Activating Token Index: 24

Text #5

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.3737. Min Act: -0.0001

Data Index: 1604409 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.3333. Min Act: -0.0001

Data Index: 1452671 (Python Code)

Max Activating Token Index: 76

Text #7

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.3296. Min Act: -0.0000

Data Index: 1591349 (Python Code)

Max Activating Token Index: 381

Text #8

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1454251 (Python Code)

Max Activating Token Index: 427

Text #9

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2545. Min Act: -0.0000

Data Index: 1384579 (Python Code)

Max Activating Token Index: 74

Text #10

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2475. Min Act: -0.0000

Data Index: 1552178 (Python Code)

Max Activating Token Index: 797

Text #11

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1375192 (Python Code)

Max Activating Token Index: 914

Text #12

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.1902. Min Act: -0.0001

Data Index: 1490412 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2234. Min Act: -0.0001

Data Index: 1363146 (Python Code)

Max Activating Token Index: 332

Text #14

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.1525. Min Act: -0.0001

Data Index: 1480669 (Python Code)

Max Activating Token Index: 361

Text #15

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2506. Min Act: -0.0000

Data Index: 1514623 (Python Code)

Max Activating Token Index: 1014

Text #16

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.1408. Min Act: -0.0001

Data Index: 1373874 (Python Code)

Max Activating Token Index: 579

Text #17

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1627957 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2096. Min Act: -0.0001

Data Index: 1428607 (Python Code)

Max Activating Token Index: 268

Text #19

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.1153. Min Act: -0.0001

Data Index: 1400648 (Python Code)

Max Activating Token Index: 60