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

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

Neuron 1391 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: 2.6392. Min Range: -2.6392

Max Act: 2.6392. Min Act: -0.0000

Data Index: 94322 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 2.6392. Min Range: -2.6392

Max Act: 2.3911. Min Act: -0.0000

Data Index: 883525 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 2.6392. Min Range: -2.6392

Max Act: 2.3544. Min Act: -0.0000

Data Index: 739129 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 2.6392. Min Range: -2.6392

Max Act: 2.2450. Min Act: -0.0000

Data Index: 137869 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.9235. Min Act: -0.0000

Data Index: 930351 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.9644. Min Act: -0.0000

Data Index: 142378 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 2.6392. Min Range: -2.6392

Max Act: 2.0673. Min Act: -0.0000

Data Index: 159207 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.8018. Min Act: -0.0000

Data Index: 1220788 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.9073. Min Act: -0.0000

Data Index: 1326094 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.7066. Min Act: -0.0000

Data Index: 52566 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.7524. Min Act: -0.0000

Data Index: 1017663 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.7601. Min Act: -0.0000

Data Index: 1038626 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.6577. Min Act: -0.0000

Data Index: 779529 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.7333. Min Act: -0.0000

Data Index: 1071884 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.6185. Min Act: -0.0000

Data Index: 1152730 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.5193. Min Act: -0.0000

Data Index: 792099 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.8804. Min Act: -0.0000

Data Index: 469011 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.7631. Min Act: -0.0000

Data Index: 556130 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.6523. Min Act: -0.0000

Data Index: 873864 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 2.6392. Min Range: -2.6392

Max Act: 1.5995. Min Act: -0.0000

Data Index: 1328701 (C4 (Web Text))

Max Activating Token Index: 99