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

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

Neuron 620 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6127. Min Range: -3.6127

Max Act: 3.6127. Min Act: -0.0000

Data Index: 1598421 (Python Code)

Max Activating Token Index: 38

Text #1

Max Range: 3.6127. Min Range: -3.6127

Max Act: 3.0828. Min Act: -0.0000

Data Index: 1554954 (Python Code)

Max Activating Token Index: 46

Text #2

Max Range: 3.6127. Min Range: -3.6127

Max Act: 3.4908. Min Act: -0.0000

Data Index: 1425658 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 3.6127. Min Range: -3.6127

Max Act: 3.3179. Min Act: -0.0000

Data Index: 1599260 (Python Code)

Max Activating Token Index: 190

Text #4

Max Range: 3.6127. Min Range: -3.6127

Max Act: 3.0807. Min Act: -0.0000

Data Index: 1407724 (Python Code)

Max Activating Token Index: 925

Text #5

Max Range: 3.6127. Min Range: -3.6127

Max Act: 3.0430. Min Act: -0.0000

Data Index: 1120150 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 3.6127. Min Range: -3.6127

Max Act: 3.0222. Min Act: -0.0000

Data Index: 254253 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 3.6127. Min Range: -3.6127

Max Act: 2.9469. Min Act: -0.0000

Data Index: 1449511 (Python Code)

Max Activating Token Index: 624

Text #8

Max Range: 3.6127. Min Range: -3.6127

Max Act: 3.0732. Min Act: -0.0000

Data Index: 1611644 (Python Code)

Max Activating Token Index: 507

Text #9

Max Range: 3.6127. Min Range: -3.6127

Max Act: 2.9515. Min Act: -0.0000

Data Index: 1380960 (Python Code)

Max Activating Token Index: 78

Text #10

Max Range: 3.6127. Min Range: -3.6127

Max Act: 2.8067. Min Act: -0.0000

Data Index: 1373257 (Python Code)

Max Activating Token Index: 336

Text #11

Max Range: 3.6127. Min Range: -3.6127

Max Act: 3.0553. Min Act: -0.0000

Data Index: 1620987 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 3.6127. Min Range: -3.6127

Max Act: 2.7855. Min Act: -0.0000

Data Index: 1520644 (Python Code)

Max Activating Token Index: 46

Text #13

Max Range: 3.6127. Min Range: -3.6127

Max Act: 2.7594. Min Act: -0.0000

Data Index: 826910 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 3.6127. Min Range: -3.6127

Max Act: 2.8890. Min Act: -0.0000

Data Index: 1640539 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 3.6127. Min Range: -3.6127

Max Act: 3.0059. Min Act: -0.0000

Data Index: 75607 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 3.6127. Min Range: -3.6127

Max Act: 2.8882. Min Act: -0.0000

Data Index: 1478651 (Python Code)

Max Activating Token Index: 177

Text #17

Max Range: 3.6127. Min Range: -3.6127

Max Act: 2.8533. Min Act: -0.0000

Data Index: 1625270 (Python Code)

Max Activating Token Index: 70

Text #18

Max Range: 3.6127. Min Range: -3.6127

Max Act: 2.8276. Min Act: -0.0000

Data Index: 1648276 (Python Code)

Max Activating Token Index: 539

Text #19

Max Range: 3.6127. Min Range: -3.6127

Max Act: 2.8027. Min Act: -0.0000

Data Index: 1618942 (Python Code)

Max Activating Token Index: 25