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

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

Neuron 2843 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0313. Min Range: -2.0313

Max Act: 2.0313. Min Act: -0.0000

Data Index: 87085 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.6628. Min Act: -0.0000

Data Index: 1249819 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.5797. Min Act: -0.0000

Data Index: 1052654 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.4277. Min Act: -0.0000

Data Index: 748461 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.4350. Min Act: -0.0000

Data Index: 793611 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.4328. Min Act: -0.0000

Data Index: 141671 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.4292. Min Act: -0.0000

Data Index: 126283 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.4176. Min Act: -0.0000

Data Index: 1014410 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.3143. Min Act: -0.0000

Data Index: 753237 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.4563. Min Act: -0.0000

Data Index: 837031 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.3774. Min Act: -0.0000

Data Index: 455683 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.4446. Min Act: -0.0000

Data Index: 577780 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.3451. Min Act: -0.0000

Data Index: 438938 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.2618. Min Act: -0.0000

Data Index: 910206 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.3322. Min Act: -0.0000

Data Index: 303038 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.3293. Min Act: -0.0001

Data Index: 1349147 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.3873. Min Act: -0.0000

Data Index: 1351612 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.3009. Min Act: -0.0000

Data Index: 1034385 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.2910. Min Act: -0.0000

Data Index: 1054208 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 2.0313. Min Range: -2.0313

Max Act: 1.2856. Min Act: -0.0000

Data Index: 1019201 (C4 (Web Text))

Max Activating Token Index: 437