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

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

Neuron 1935 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9729. Min Range: -3.9729

Max Act: 3.9729. Min Act: -0.0000

Data Index: 942663 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 3.9729. Min Range: -3.9729

Max Act: 3.3179. Min Act: -0.0000

Data Index: 789845 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 3.9729. Min Range: -3.9729

Max Act: 3.2766. Min Act: -0.0000

Data Index: 331370 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 3.9729. Min Range: -3.9729

Max Act: 3.0996. Min Act: -0.0000

Data Index: 987180 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 3.9729. Min Range: -3.9729

Max Act: 3.0287. Min Act: -0.0000

Data Index: 1114916 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.8603. Min Act: -0.0000

Data Index: 1198600 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.7523. Min Act: -0.0000

Data Index: 650913 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.8465. Min Act: -0.0000

Data Index: 965250 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.8524. Min Act: -0.0000

Data Index: 233579 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.6080. Min Act: -0.0000

Data Index: 1243848 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.7315. Min Act: -0.0000

Data Index: 650945 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.7092. Min Act: -0.0000

Data Index: 1277473 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.5471. Min Act: -0.0000

Data Index: 809388 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.5339. Min Act: -0.0000

Data Index: 197962 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.7515. Min Act: -0.0000

Data Index: 1317606 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.5653. Min Act: -0.0000

Data Index: 1044961 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.5534. Min Act: -0.0000

Data Index: 718015 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.5330. Min Act: -0.0000

Data Index: 1228651 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.5487. Min Act: -0.0000

Data Index: 535390 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.5421. Min Act: -0.0000

Data Index: 1157093 (C4 (Web Text))

Max Activating Token Index: 944