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

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

Neuron 3895 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7377. Min Range: -2.7377

Max Act: 2.7377. Min Act: -0.0000

Data Index: 1312815 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 2.7377. Min Range: -2.7377

Max Act: 1.3644. Min Act: -0.0000

Data Index: 119420 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 2.7377. Min Range: -2.7377

Max Act: 1.2875. Min Act: -0.0000

Data Index: 1094987 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1026952 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 2.7377. Min Range: -2.7377

Max Act: 1.0212. Min Act: -0.0000

Data Index: 821938 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0130. Min Act: -0.0000

Data Index: 243404 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0369. Min Act: -0.0000

Data Index: 1097468 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0281. Min Act: -0.0000

Data Index: 1275402 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0507. Min Act: -0.0000

Data Index: 38584 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0461. Min Act: -0.0000

Data Index: 63496 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0387. Min Act: -0.0000

Data Index: 934868 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0532. Min Act: -0.0000

Data Index: 117007 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0377. Min Act: -0.0000

Data Index: 347171 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0381. Min Act: -0.0000

Data Index: 400775 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0416. Min Act: -0.0000

Data Index: 986023 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0227. Min Act: -0.0000

Data Index: 796665 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0199. Min Act: -0.0000

Data Index: 223933 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0700. Min Act: -0.0000

Data Index: 556598 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0336. Min Act: -0.0000

Data Index: 307708 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 2.7377. Min Range: -2.7377

Max Act: 0.0299. Min Act: -0.0000

Data Index: 242766 (C4 (Web Text))

Max Activating Token Index: 196