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

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

Neuron 1018 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.5092. Min Act: -0.0000

Data Index: 848412 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.3235. Min Act: -0.0000

Data Index: 415192 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.2548. Min Act: -0.0000

Data Index: 1342398 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.2504. Min Act: -0.0000

Data Index: 436160 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 1.5092. Min Range: -1.5092

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1239266 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1104490 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.9610. Min Act: -0.0000

Data Index: 326709 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1092790 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.8706. Min Act: -0.0000

Data Index: 947581 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.8271. Min Act: -0.0000

Data Index: 123075 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.8503. Min Act: -0.0000

Data Index: 607205 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.8103. Min Act: -0.0000

Data Index: 96870 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1614204 (Python Code)

Max Activating Token Index: 138

Text #13

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.8950. Min Act: -0.0000

Data Index: 428114 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.6813. Min Act: -0.0000

Data Index: 677414 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1279408 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.7337. Min Act: -0.0000

Data Index: 205111 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.7563. Min Act: -0.0000

Data Index: 69372 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.7385. Min Act: -0.0000

Data Index: 612487 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 1.5092. Min Range: -1.5092

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1254647 (C4 (Web Text))

Max Activating Token Index: 153