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

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

Neuron 2849 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2746. Min Act: -0.0000

Data Index: 29026 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2566. Min Act: -0.0000

Data Index: 424690 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2556. Min Act: -0.0001

Data Index: 1239823 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2477. Min Act: -0.0001

Data Index: 16114 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2438. Min Act: -0.0001

Data Index: 51660 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2391. Min Act: -0.0001

Data Index: 1233908 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2357. Min Act: -0.0000

Data Index: 348622 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2193. Min Act: -0.0001

Data Index: 1221306 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1166700 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2216. Min Act: -0.0000

Data Index: 887243 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2133. Min Act: -0.0000

Data Index: 548667 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1248164 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2189. Min Act: -0.0000

Data Index: 819615 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2181. Min Act: -0.0001

Data Index: 85655 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2070. Min Act: -0.0000

Data Index: 9533 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2039. Min Act: -0.0001

Data Index: 640462 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1258507 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2107. Min Act: -0.0001

Data Index: 341867 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2098. Min Act: -0.0000

Data Index: 580861 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2094. Min Act: -0.0001

Data Index: 959161 (C4 (Web Text))

Max Activating Token Index: 970