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

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

Neuron 3599 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.3441. Min Act: -0.0000

Data Index: 692324 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1211084 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1331075 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2788. Min Act: -0.0000

Data Index: 872580 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.3042. Min Act: -0.0000

Data Index: 609808 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.3017. Min Act: -0.0000

Data Index: 898546 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1005066 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2596. Min Act: -0.0000

Data Index: 740181 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1231921 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1172475 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1182357 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2513. Min Act: -0.0000

Data Index: 794771 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2438. Min Act: -0.0000

Data Index: 338179 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1129260 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2416. Min Act: -0.0000

Data Index: 464663 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1242742 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2194. Min Act: -0.0000

Data Index: 422562 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2088. Min Act: -0.0000

Data Index: 875219 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2216. Min Act: -0.0000

Data Index: 67926 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2192. Min Act: 0.0000

Data Index: 621908 (C4 (Web Text))

Max Activating Token Index: 543