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

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

Neuron 5062 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3417. Min Act: -0.0000

Data Index: 54275 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3229. Min Act: -0.0000

Data Index: 503959 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3373. Min Act: -0.0000

Data Index: 218666 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2843. Min Act: -0.0000

Data Index: 7723 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2870. Min Act: -0.0000

Data Index: 532179 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1244478 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2669. Min Act: -0.0000

Data Index: 13301 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2843. Min Act: -0.0000

Data Index: 516500 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1354079 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2745. Min Act: -0.0000

Data Index: 348086 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2729. Min Act: -0.0000

Data Index: 712659 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2628. Min Act: -0.0000

Data Index: 766304 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2589. Min Act: -0.0000

Data Index: 722027 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2400. Min Act: -0.0000

Data Index: 455488 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2453. Min Act: -0.0000

Data Index: 540470 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2529. Min Act: -0.0000

Data Index: 542502 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1208628 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2301. Min Act: -0.0000

Data Index: 996950 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2535. Min Act: -0.0000

Data Index: 164749 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2222. Min Act: -0.0000

Data Index: 983653 (C4 (Web Text))

Max Activating Token Index: 69