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

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

Neuron 2432 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: 2.2642. Min Range: -2.2642

Max Act: 2.2642. Min Act: -0.0000

Data Index: 1132779 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 2.2642. Min Range: -2.2642

Max Act: 2.2431. Min Act: -0.0000

Data Index: 1094183 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.6790. Min Act: -0.0000

Data Index: 100485 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.5956. Min Act: -0.0000

Data Index: 1304426 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.6189. Min Act: -0.0000

Data Index: 1160758 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.7280. Min Act: -0.0000

Data Index: 619442 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.5731. Min Act: -0.0000

Data Index: 169356 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.3738. Min Act: -0.0000

Data Index: 362315 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.4748. Min Act: -0.0000

Data Index: 333270 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.5062. Min Act: -0.0000

Data Index: 126276 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.3991. Min Act: -0.0000

Data Index: 722389 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.3710. Min Act: -0.0000

Data Index: 315680 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.2506. Min Act: -0.0000

Data Index: 1162842 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.3511. Min Act: -0.0000

Data Index: 122514 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.2097. Min Act: -0.0000

Data Index: 869392 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.2551. Min Act: -0.0000

Data Index: 110662 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.2443. Min Act: -0.0000

Data Index: 1200827 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.2338. Min Act: -0.0000

Data Index: 769302 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.2655. Min Act: -0.0000

Data Index: 1353733 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 2.2642. Min Range: -2.2642

Max Act: 1.2600. Min Act: -0.0000

Data Index: 1004138 (C4 (Web Text))

Max Activating Token Index: 405