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

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

Neuron 2085 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: 3.6449. Min Range: -3.6449

Max Act: 3.6449. Min Act: -0.0000

Data Index: 2196 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.3403. Min Act: -0.0000

Data Index: 348046 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.5001. Min Act: -0.0000

Data Index: 248076 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.2834. Min Act: -0.0000

Data Index: 1637784 (Python Code)

Max Activating Token Index: 896

Text #4

Max Range: 3.6449. Min Range: -3.6449

Max Act: 2.9033. Min Act: -0.0000

Data Index: 416982 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 3.6449. Min Range: -3.6449

Max Act: 2.9488. Min Act: -0.0000

Data Index: 970056 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 3.6449. Min Range: -3.6449

Max Act: 2.8832. Min Act: -0.0000

Data Index: 1447281 (Python Code)

Max Activating Token Index: 984

Text #7

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.1273. Min Act: -0.0000

Data Index: 1558054 (Python Code)

Max Activating Token Index: 557

Text #8

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.1117. Min Act: -0.0000

Data Index: 931244 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.1076. Min Act: -0.0000

Data Index: 329961 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.0704. Min Act: -0.0000

Data Index: 1013317 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.0490. Min Act: -0.0000

Data Index: 852827 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 3.6449. Min Range: -3.6449

Max Act: 2.8645. Min Act: -0.0000

Data Index: 675331 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 3.6449. Min Range: -3.6449

Max Act: 2.9842. Min Act: -0.0000

Data Index: 1466071 (Python Code)

Max Activating Token Index: 672

Text #14

Max Range: 3.6449. Min Range: -3.6449

Max Act: 2.9901. Min Act: -0.0000

Data Index: 1606785 (Python Code)

Max Activating Token Index: 753

Text #15

Max Range: 3.6449. Min Range: -3.6449

Max Act: 2.9544. Min Act: -0.0000

Data Index: 750458 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 3.6449. Min Range: -3.6449

Max Act: 2.8987. Min Act: -0.0000

Data Index: 205093 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 3.6449. Min Range: -3.6449

Max Act: 2.7269. Min Act: -0.0000

Data Index: 555630 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 3.6449. Min Range: -3.6449

Max Act: 2.7018. Min Act: -0.0000

Data Index: 1056565 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 3.6449. Min Range: -3.6449

Max Act: 2.7820. Min Act: -0.0000

Data Index: 1449559 (Python Code)

Max Activating Token Index: 686