Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4155 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.8712. Min Act: -0.0001

Data Index: 166403 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.8889. Min Act: -0.0001

Data Index: 54707 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.7168. Min Act: -0.0001

Data Index: 556725 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.2463. Min Act: -0.0001

Data Index: 1299958 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.9036. Min Act: -0.0001

Data Index: 135305 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.8702. Min Act: -0.0001

Data Index: 1244137 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.7327. Min Act: -0.0001

Data Index: 961498 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.5607. Min Act: -0.0001

Data Index: 544065 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.7121. Min Act: -0.0001

Data Index: 804503 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.5785. Min Act: -0.0001

Data Index: 300945 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.4380. Min Act: -0.0001

Data Index: 118491 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.5519. Min Act: -0.0001

Data Index: 1346062 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.7417. Min Act: -0.0001

Data Index: 181519 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.3917. Min Act: -0.0001

Data Index: 787054 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.4491. Min Act: -0.0001

Data Index: 821791 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.3922. Min Act: -0.0001

Data Index: 53025 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.7594. Min Act: -0.0001

Data Index: 1112307 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.2737. Min Act: -0.0001

Data Index: 600304 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.3735. Min Act: -0.0001

Data Index: 138153 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.1256. Min Act: -0.0001

Data Index: 677946 (C4 (Web Text))

Max Activating Token Index: 66