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

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

Neuron 4048 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.9414. Min Act: -0.0000

Data Index: 770047 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.2729. Min Act: -0.0000

Data Index: 890838 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.0929. Min Act: -0.0000

Data Index: 1154202 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.9347. Min Act: -0.0000

Data Index: 499125 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.0036. Min Act: -0.0000

Data Index: 1527994 (Python Code)

Max Activating Token Index: 677

Text #5

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.8953. Min Act: -0.0000

Data Index: 806539 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.9793. Min Act: -0.0000

Data Index: 1436367 (Python Code)

Max Activating Token Index: 462

Text #7

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.0829. Min Act: -0.0000

Data Index: 939572 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.8362. Min Act: -0.0000

Data Index: 1311629 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.7148. Min Act: -0.0000

Data Index: 889792 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.7134. Min Act: -0.0000

Data Index: 306714 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.6893. Min Act: -0.0000

Data Index: 677093 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.6666. Min Act: -0.0000

Data Index: 1111450 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.6058. Min Act: -0.0000

Data Index: 1312047 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.6126. Min Act: -0.0000

Data Index: 417474 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.6694. Min Act: -0.0000

Data Index: 281485 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.4602. Min Act: -0.0000

Data Index: 758438 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.5359. Min Act: -0.0000

Data Index: 315259 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.5075. Min Act: -0.0000

Data Index: 1233728 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.4276. Min Act: -0.0000

Data Index: 793916 (C4 (Web Text))

Max Activating Token Index: 708