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

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

Neuron 1830 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1050. Min Range: -4.1050

Max Act: 4.1050. Min Act: -0.0000

Data Index: 772772 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 4.1050. Min Range: -4.1050

Max Act: 3.3403. Min Act: -0.0000

Data Index: 878778 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.9759. Min Act: -0.0000

Data Index: 946036 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 4.1050. Min Range: -4.1050

Max Act: 3.0920. Min Act: -0.0000

Data Index: 646814 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.8843. Min Act: -0.0000

Data Index: 56282 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.8438. Min Act: -0.0000

Data Index: 123806 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.8247. Min Act: -0.0000

Data Index: 1148098 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.5160. Min Act: -0.0000

Data Index: 317563 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.8111. Min Act: -0.0000

Data Index: 1063471 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.5882. Min Act: -0.0000

Data Index: 229012 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.2249. Min Act: -0.0000

Data Index: 869673 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.5869. Min Act: -0.0000

Data Index: 979690 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.5908. Min Act: -0.0000

Data Index: 932887 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.4378. Min Act: -0.0000

Data Index: 1308997 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.5707. Min Act: -0.0000

Data Index: 341395 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.5502. Min Act: -0.0000

Data Index: 414680 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.2509. Min Act: -0.0000

Data Index: 448683 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.5773. Min Act: -0.0000

Data Index: 1175113 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.4543. Min Act: -0.0000

Data Index: 364525 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 4.1050. Min Range: -4.1050

Max Act: 2.4027. Min Act: -0.0000

Data Index: 210438 (C4 (Web Text))

Max Activating Token Index: 675