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

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

Neuron 5692 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.3486. Min Act: -0.0002

Data Index: 1045364 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.2515. Min Act: -0.0002

Data Index: 445366 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.2051. Min Act: -0.0002

Data Index: 148352 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.1953. Min Act: -0.0002

Data Index: 225073 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.2123. Min Act: -0.0002

Data Index: 1292792 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.1775. Min Act: -0.0002

Data Index: 644303 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.1713. Min Act: -0.0002

Data Index: 940785 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.1355. Min Act: -0.0002

Data Index: 799742 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.1489. Min Act: -0.0002

Data Index: 269839 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.1539. Min Act: -0.0002

Data Index: 1357726 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.1210. Min Act: -0.0002

Data Index: 38789 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.1223. Min Act: -0.0002

Data Index: 1030198 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.1061. Min Act: -0.0002

Data Index: 77936 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.1006. Min Act: -0.0002

Data Index: 401226 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.1035. Min Act: -0.0002

Data Index: 442497 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.1060. Min Act: -0.0002

Data Index: 1097661 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.0767. Min Act: -0.0002

Data Index: 95213 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.0778. Min Act: -0.0002

Data Index: 316122 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.0805. Min Act: -0.0002

Data Index: 320986 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 1.3486. Min Range: -1.3486

Max Act: 1.0925. Min Act: -0.0002

Data Index: 805059 (C4 (Web Text))

Max Activating Token Index: 879