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

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

Neuron 255 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4432. Min Act: -0.0000

Data Index: 791655 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1286441 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4089. Min Act: -0.0000

Data Index: 516653 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1220214 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4047. Min Act: -0.0000

Data Index: 485558 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1023175 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4334. Min Act: -0.0000

Data Index: 770987 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1179208 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4047. Min Act: -0.0000

Data Index: 707971 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1274045 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3953. Min Act: -0.0000

Data Index: 388568 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3900. Min Act: -0.0000

Data Index: 584757 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3834. Min Act: -0.0000

Data Index: 968668 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3812. Min Act: -0.0000

Data Index: 825971 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1186333 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3589. Min Act: -0.0000

Data Index: 326955 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3754. Min Act: -0.0000

Data Index: 361593 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4001. Min Act: -0.0000

Data Index: 26076 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3704. Min Act: -0.0000

Data Index: 450589 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1353161 (C4 (Web Text))

Max Activating Token Index: 989