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

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

Neuron 1580 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: 0.3246. Min Range: -0.3246

Max Act: 0.3195. Min Act: -0.0000

Data Index: 728041 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.3246. Min Act: -0.0000

Data Index: 860209 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.3014. Min Act: -0.0000

Data Index: 259915 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2858. Min Act: -0.0000

Data Index: 290567 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2751. Min Act: -0.0000

Data Index: 681336 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1209418 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2838. Min Act: -0.0000

Data Index: 890655 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1354834 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2779. Min Act: -0.0000

Data Index: 737350 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1089894 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2760. Min Act: -0.0000

Data Index: 632950 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1161514 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2673. Min Act: -0.0000

Data Index: 60108 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2558. Min Act: -0.0000

Data Index: 441117 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1283478 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2529. Min Act: -0.0000

Data Index: 309645 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2566. Min Act: -0.0000

Data Index: 310946 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1313692 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2526. Min Act: -0.0000

Data Index: 220167 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2395. Min Act: -0.0000

Data Index: 111516 (C4 (Web Text))

Max Activating Token Index: 604