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

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

Neuron 2785 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.8592. Min Act: -0.0000

Data Index: 864148 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.8193. Min Act: -0.0000

Data Index: 728391 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7141. Min Act: -0.0000

Data Index: 752703 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.8161. Min Act: -0.0000

Data Index: 896580 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7112. Min Act: -0.0000

Data Index: 749439 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6932. Min Act: -0.0000

Data Index: 131865 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1289746 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1618648 (Python Code)

Max Activating Token Index: 187

Text #8

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1208112 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5728. Min Act: -0.0000

Data Index: 500023 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6899. Min Act: -0.0000

Data Index: 436256 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1178605 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6283. Min Act: -0.0000

Data Index: 352853 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5769. Min Act: -0.0000

Data Index: 724704 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5935. Min Act: -0.0000

Data Index: 433472 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1026122 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1074624 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5370. Min Act: -0.0000

Data Index: 969951 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5960. Min Act: -0.0000

Data Index: 643528 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.5092. Min Act: -0.0000

Data Index: 635204 (C4 (Web Text))

Max Activating Token Index: 818