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

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

Neuron 57 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.6166. Min Act: -0.0000

Data Index: 922413 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1246563 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5614. Min Act: -0.0000

Data Index: 883049 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5218. Min Act: -0.0000

Data Index: 1338763 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4488. Min Act: -0.0000

Data Index: 12050 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4769. Min Act: -0.0000

Data Index: 167341 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1091644 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4637. Min Act: -0.0000

Data Index: 870666 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4646. Min Act: -0.0000

Data Index: 907413 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4603. Min Act: -0.0000

Data Index: 843139 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4108. Min Act: -0.0000

Data Index: 724007 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4203. Min Act: -0.0000

Data Index: 822047 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4217. Min Act: -0.0000

Data Index: 621153 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1216876 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4266. Min Act: -0.0000

Data Index: 989013 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4183. Min Act: -0.0000

Data Index: 273776 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1234724 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.3813. Min Act: -0.0000

Data Index: 268481 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.3809. Min Act: -0.0000

Data Index: 104937 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.3935. Min Act: -0.0000

Data Index: 958789 (C4 (Web Text))

Max Activating Token Index: 276