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

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

Neuron 2733 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: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.0000

Data Index: 762723 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.4953. Min Act: -0.0000

Data Index: 948857 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.3388. Min Act: -0.0000

Data Index: 1211716 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.0220. Min Act: -0.0000

Data Index: 354860 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.1304. Min Act: -0.0000

Data Index: 100023 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.0943. Min Act: -0.0000

Data Index: 1318791 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.0725. Min Act: -0.0000

Data Index: 733844 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.9959. Min Act: -0.0000

Data Index: 669523 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.9937. Min Act: -0.0000

Data Index: 221555 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.9517. Min Act: -0.0000

Data Index: 754559 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.9463. Min Act: -0.0000

Data Index: 125261 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.8867. Min Act: -0.0000

Data Index: 703614 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.8660. Min Act: -0.0000

Data Index: 1004005 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.8609. Min Act: -0.0000

Data Index: 841906 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.8363. Min Act: -0.0000

Data Index: 121929 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.7771. Min Act: -0.0000

Data Index: 528987 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.7469. Min Act: -0.0000

Data Index: 810076 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.8693. Min Act: -0.0000

Data Index: 1190156 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.5279. Min Act: -0.0000

Data Index: 1300872 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.7716. Min Act: -0.0000

Data Index: 990815 (C4 (Web Text))

Max Activating Token Index: 281