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

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

Neuron 1742 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: 2.4566. Min Range: -2.4566

Max Act: 2.4566. Min Act: -0.0000

Data Index: 526238 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.5221. Min Act: -0.0000

Data Index: 816650 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.4712. Min Act: -0.0000

Data Index: 579179 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.4613. Min Act: -0.0000

Data Index: 830106 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.4095. Min Act: -0.0000

Data Index: 60709 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.4283. Min Act: -0.0000

Data Index: 681521 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.4033. Min Act: -0.0000

Data Index: 542055 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.1865. Min Act: -0.0000

Data Index: 71501 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.4162. Min Act: -0.0000

Data Index: 149697 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1173709 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.3790. Min Act: -0.0000

Data Index: 555188 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.3908. Min Act: -0.0000

Data Index: 230402 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.3860. Min Act: -0.0000

Data Index: 651003 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.3786. Min Act: -0.0000

Data Index: 634956 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.3823. Min Act: -0.0000

Data Index: 681180 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.3597. Min Act: -0.0000

Data Index: 679281 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.3535. Min Act: -0.0000

Data Index: 324190 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.3460. Min Act: -0.0000

Data Index: 154166 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.3719. Min Act: -0.0000

Data Index: 879243 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 2.4566. Min Range: -2.4566

Max Act: 0.3534. Min Act: 0.0000

Data Index: 634567 (C4 (Web Text))

Max Activating Token Index: 733