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

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

Neuron 4076 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: 2.3080. Min Range: -2.3080

Max Act: 2.3080. Min Act: -0.0000

Data Index: 1032593 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 2.3080. Min Range: -2.3080

Max Act: 2.2703. Min Act: -0.0000

Data Index: 217006 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 2.3080. Min Range: -2.3080

Max Act: 2.2475. Min Act: -0.0000

Data Index: 776718 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 2.3080. Min Range: -2.3080

Max Act: 2.2701. Min Act: -0.0000

Data Index: 953250 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.8523. Min Act: -0.0000

Data Index: 344685 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.9582. Min Act: -0.0000

Data Index: 61998 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.8834. Min Act: -0.0000

Data Index: 1269322 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.8852. Min Act: -0.0000

Data Index: 1008037 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.5048. Min Act: -0.0000

Data Index: 1294638 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.4865. Min Act: -0.0000

Data Index: 96530 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.4869. Min Act: -0.0000

Data Index: 1294744 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.2510. Min Act: -0.0000

Data Index: 748568 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.2573. Min Act: -0.0000

Data Index: 669780 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.2360. Min Act: -0.0000

Data Index: 274626 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.3796. Min Act: -0.0000

Data Index: 172966 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.3438. Min Act: -0.0000

Data Index: 579770 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.2531. Min Act: -0.0000

Data Index: 57954 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.2549. Min Act: -0.0000

Data Index: 1015154 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.2208. Min Act: -0.0000

Data Index: 1351117 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 2.3080. Min Range: -2.3080

Max Act: 1.2011. Min Act: -0.0000

Data Index: 1117855 (C4 (Web Text))

Max Activating Token Index: 559