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

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

Neuron 2640 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: 1.5151. Min Range: -1.5151

Max Act: 1.5151. Min Act: -0.0000

Data Index: 1163977 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.2760. Min Act: -0.0000

Data Index: 944142 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.2507. Min Act: -0.0000

Data Index: 1130709 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.2534. Min Act: -0.0000

Data Index: 376305 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.2417. Min Act: -0.0000

Data Index: 762405 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.2416. Min Act: -0.0000

Data Index: 718559 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.1511. Min Act: -0.0000

Data Index: 235729 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.2167. Min Act: -0.0000

Data Index: 1018185 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.1931. Min Act: -0.0000

Data Index: 883753 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.1128. Min Act: -0.0000

Data Index: 916860 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.2518. Min Act: -0.0000

Data Index: 279356 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.1710. Min Act: -0.0000

Data Index: 1276116 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.1673. Min Act: -0.0000

Data Index: 79383 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.1729. Min Act: -0.0000

Data Index: 173176 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.2102. Min Act: -0.0000

Data Index: 1308142 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.1301. Min Act: -0.0000

Data Index: 46340 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.1339. Min Act: -0.0000

Data Index: 806492 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.1207. Min Act: -0.0000

Data Index: 567738 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.1064. Min Act: -0.0000

Data Index: 1066317 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 1.5151. Min Range: -1.5151

Max Act: 1.1065. Min Act: -0.0000

Data Index: 42499 (C4 (Web Text))

Max Activating Token Index: 1001