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

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

Neuron 3852 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2513. Min Range: -4.2513

Max Act: 4.2513. Min Act: -0.0000

Data Index: 820378 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 4.2513. Min Range: -4.2513

Max Act: 4.2478. Min Act: -0.0000

Data Index: 36075 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 4.2513. Min Range: -4.2513

Max Act: 4.1871. Min Act: -0.0000

Data Index: 1171720 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 4.2513. Min Range: -4.2513

Max Act: 4.1672. Min Act: -0.0000

Data Index: 699808 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.8851. Min Act: -0.0000

Data Index: 910852 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.8834. Min Act: -0.0000

Data Index: 995752 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.8785. Min Act: -0.0000

Data Index: 994306 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.8200. Min Act: -0.0000

Data Index: 878471 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.6264. Min Act: -0.0000

Data Index: 874563 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.4970. Min Act: -0.0000

Data Index: 757069 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.6049. Min Act: -0.0000

Data Index: 1300473 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.6240. Min Act: -0.0000

Data Index: 587172 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.7717. Min Act: -0.0000

Data Index: 1240992 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.5971. Min Act: -0.0000

Data Index: 109157 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.4274. Min Act: -0.0000

Data Index: 18725 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.6869. Min Act: -0.0000

Data Index: 239577 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.5090. Min Act: -0.0000

Data Index: 587618 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.3160. Min Act: -0.0000

Data Index: 1203908 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.3408. Min Act: -0.0000

Data Index: 757199 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 4.2513. Min Range: -4.2513

Max Act: 3.1660. Min Act: -0.0000

Data Index: 152995 (C4 (Web Text))

Max Activating Token Index: 264