Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3458 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.6221. Min Act: -0.0000

Data Index: 1333011 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.6170. Min Act: -0.0000

Data Index: 1557222 (Python Code)

Max Activating Token Index: 235

Text #2

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.5282. Min Act: -0.0000

Data Index: 988191 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.5564. Min Act: -0.0000

Data Index: 1542685 (Python Code)

Max Activating Token Index: 274

Text #4

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.4644. Min Act: -0.0000

Data Index: 1369419 (Python Code)

Max Activating Token Index: 248

Text #5

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.3707. Min Act: -0.0000

Data Index: 1456204 (Python Code)

Max Activating Token Index: 39

Text #6

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.2704. Min Act: -0.0000

Data Index: 1617793 (Python Code)

Max Activating Token Index: 931

Text #7

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.4007. Min Act: -0.0000

Data Index: 1407762 (Python Code)

Max Activating Token Index: 65

Text #8

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.3045. Min Act: -0.0000

Data Index: 1529557 (Python Code)

Max Activating Token Index: 90

Text #9

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.2983. Min Act: -0.0000

Data Index: 1509063 (Python Code)

Max Activating Token Index: 75

Text #10

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.3704. Min Act: -0.0000

Data Index: 923525 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.2942. Min Act: -0.0000

Data Index: 1405466 (Python Code)

Max Activating Token Index: 178

Text #12

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.3596. Min Act: -0.0000

Data Index: 1391729 (Python Code)

Max Activating Token Index: 1005

Text #13

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.3490. Min Act: -0.0000

Data Index: 1478840 (Python Code)

Max Activating Token Index: 76

Text #14

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.3253. Min Act: -0.0000

Data Index: 1427832 (Python Code)

Max Activating Token Index: 288

Text #15

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.2307. Min Act: -0.0000

Data Index: 1562958 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1631709 (Python Code)

Max Activating Token Index: 66

Text #17

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1503151 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.2587. Min Act: -0.0000

Data Index: 1409661 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 1.6221. Min Range: -1.6221

Max Act: 1.1933. Min Act: -0.0000

Data Index: 1599725 (Python Code)

Max Activating Token Index: 565