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

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

Neuron 1010 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.9228. Min Act: -0.0000

Data Index: 693810 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.7762. Min Act: -0.0000

Data Index: 674829 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.4454. Min Act: -0.0000

Data Index: 1109739 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.5576. Min Act: -0.0000

Data Index: 1288123 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.5194. Min Act: -0.0000

Data Index: 605182 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.0153. Min Act: -0.0000

Data Index: 1067004 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 2.9228. Min Range: -2.9228

Max Act: 1.7488. Min Act: -0.0000

Data Index: 407012 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 2.9228. Min Range: -2.9228

Max Act: 1.4915. Min Act: -0.0000

Data Index: 839408 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 2.9228. Min Range: -2.9228

Max Act: 1.5931. Min Act: -0.0000

Data Index: 696126 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 2.9228. Min Range: -2.9228

Max Act: 1.5696. Min Act: -0.0000

Data Index: 690636 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 2.9228. Min Range: -2.9228

Max Act: 1.5272. Min Act: -0.0000

Data Index: 682357 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 2.9228. Min Range: -2.9228

Max Act: 1.3449. Min Act: -0.0000

Data Index: 20218 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 2.9228. Min Range: -2.9228

Max Act: 1.5166. Min Act: -0.0000

Data Index: 857248 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 2.9228. Min Range: -2.9228

Max Act: 1.4248. Min Act: -0.0000

Data Index: 229702 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 2.9228. Min Range: -2.9228

Max Act: 1.2471. Min Act: -0.0000

Data Index: 582015 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 2.9228. Min Range: -2.9228

Max Act: 1.3589. Min Act: -0.0000

Data Index: 201461 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 2.9228. Min Range: -2.9228

Max Act: 1.5059. Min Act: -0.0000

Data Index: 1032113 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 2.9228. Min Range: -2.9228

Max Act: 1.3619. Min Act: -0.0000

Data Index: 98698 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 2.9228. Min Range: -2.9228

Max Act: 1.4772. Min Act: -0.0000

Data Index: 419126 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 2.9228. Min Range: -2.9228

Max Act: 1.2998. Min Act: -0.0000

Data Index: 198450 (C4 (Web Text))

Max Activating Token Index: 520