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

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

Neuron 2782 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: 5.4092. Min Range: -5.4092

Max Act: 5.4092. Min Act: -0.0000

Data Index: 1157396 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 5.4092. Min Range: -5.4092

Max Act: 4.9090. Min Act: -0.0001

Data Index: 759178 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 5.4092. Min Range: -5.4092

Max Act: 4.1955. Min Act: -0.0000

Data Index: 4954 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.8543. Min Act: -0.0000

Data Index: 1184876 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 5.4092. Min Range: -5.4092

Max Act: 4.1393. Min Act: -0.0000

Data Index: 145468 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.9962. Min Act: -0.0001

Data Index: 365298 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.8063. Min Act: -0.0000

Data Index: 711497 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.9532. Min Act: -0.0000

Data Index: 144319 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.6548. Min Act: -0.0001

Data Index: 878066 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.5952. Min Act: -0.0000

Data Index: 867587 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.7568. Min Act: -0.0001

Data Index: 1166322 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.5499. Min Act: -0.0000

Data Index: 461773 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.6773. Min Act: -0.0000

Data Index: 191973 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.5193. Min Act: -0.0001

Data Index: 623393 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.6572. Min Act: -0.0001

Data Index: 735545 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.6429. Min Act: -0.0001

Data Index: 338599 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.4305. Min Act: -0.0000

Data Index: 790080 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 5.4092. Min Range: -5.4092

Max Act: 4.1319. Min Act: -0.0000

Data Index: 727004 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.4864. Min Act: -0.0000

Data Index: 727111 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 5.4092. Min Range: -5.4092

Max Act: 3.4857. Min Act: -0.0000

Data Index: 413477 (C4 (Web Text))

Max Activating Token Index: 693