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

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

Neuron 3065 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0922. Min Range: -2.0922

Max Act: 2.0922. Min Act: -0.0001

Data Index: 900412 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.2559. Min Act: -0.0000

Data Index: 873170 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.7636. Min Act: -0.0001

Data Index: 1322536 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.6655. Min Act: -0.0001

Data Index: 925915 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.6448. Min Act: -0.0000

Data Index: 270515 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.4752. Min Act: -0.0001

Data Index: 830157 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.4685. Min Act: -0.0001

Data Index: 1052509 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.4638. Min Act: -0.0001

Data Index: 1349472 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.6213. Min Act: -0.0000

Data Index: 463619 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.3373. Min Act: -0.0000

Data Index: 1208417 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.4341. Min Act: -0.0000

Data Index: 400492 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.4068. Min Act: -0.0000

Data Index: 389408 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.2894. Min Act: -0.0000

Data Index: 373312 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.4132. Min Act: -0.0001

Data Index: 18933 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.2466. Min Act: -0.0000

Data Index: 225067 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.3973. Min Act: -0.0001

Data Index: 945777 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.3227. Min Act: -0.0000

Data Index: 878480 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.1772. Min Act: -0.0001

Data Index: 1093290 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.3499. Min Act: -0.0000

Data Index: 1043829 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 2.0922. Min Range: -2.0922

Max Act: 1.4018. Min Act: -0.0001

Data Index: 745895 (C4 (Web Text))

Max Activating Token Index: 645