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

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

Neuron 3675 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: 0.3274. Min Range: -0.3274

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1181540 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.3207. Min Act: -0.0000

Data Index: 372610 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2988. Min Act: -0.0000

Data Index: 701518 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2846. Min Act: -0.0000

Data Index: 370223 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2797. Min Act: -0.0000

Data Index: 1122603 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2776. Min Act: 0.0000

Data Index: 1339590 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2676. Min Act: -0.0000

Data Index: 930799 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2683. Min Act: -0.0000

Data Index: 276084 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2675. Min Act: -0.0000

Data Index: 988799 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.3121. Min Act: -0.0000

Data Index: 444861 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1056638 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2627. Min Act: -0.0000

Data Index: 438025 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2527. Min Act: -0.0000

Data Index: 624601 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2625. Min Act: -0.0000

Data Index: 296281 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1028099 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1157494 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2643. Min Act: -0.0000

Data Index: 414309 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2557. Min Act: -0.0000

Data Index: 44097 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2541. Min Act: -0.0000

Data Index: 426645 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1340559 (C4 (Web Text))

Max Activating Token Index: 72