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

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

Neuron 3843 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9446. Min Act: -0.0000

Data Index: 553542 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 1.0079. Min Range: -1.0079

Max Act: 1.0079. Min Act: -0.0000

Data Index: 598384 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9166. Min Act: -0.0000

Data Index: 75741 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1296413 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9480. Min Act: -0.0000

Data Index: 70830 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8688. Min Act: -0.0001

Data Index: 358469 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8176. Min Act: -0.0000

Data Index: 682735 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8426. Min Act: -0.0000

Data Index: 96578 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1093236 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1001185 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8096. Min Act: -0.0000

Data Index: 249197 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7544. Min Act: -0.0001

Data Index: 786140 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7678. Min Act: -0.0000

Data Index: 544702 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8126. Min Act: -0.0000

Data Index: 412048 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1269577 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.6664. Min Act: -0.0000

Data Index: 136620 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7909. Min Act: -0.0000

Data Index: 549951 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7213. Min Act: -0.0000

Data Index: 638400 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7804. Min Act: -0.0000

Data Index: 1200340 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7590. Min Act: -0.0000

Data Index: 58633 (C4 (Web Text))

Max Activating Token Index: 434