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

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

Neuron 152 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4776. Min Range: -3.4776

Max Act: 3.4776. Min Act: -0.0000

Data Index: 121605 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.8965. Min Act: -0.0000

Data Index: 1167917 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 3.4776. Min Range: -3.4776

Max Act: 3.0105. Min Act: -0.0000

Data Index: 424565 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.9901. Min Act: -0.0000

Data Index: 175765 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.9520. Min Act: -0.0000

Data Index: 243846 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.9266. Min Act: -0.0000

Data Index: 474898 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.6160. Min Act: -0.0000

Data Index: 389492 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.5946. Min Act: -0.0000

Data Index: 757328 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.4421. Min Act: -0.0000

Data Index: 1134462 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.5585. Min Act: -0.0000

Data Index: 135039 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.3468. Min Act: -0.0000

Data Index: 32558 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.3225. Min Act: -0.0000

Data Index: 1028347 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.2293. Min Act: -0.0000

Data Index: 758067 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.5820. Min Act: -0.0000

Data Index: 684355 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.2968. Min Act: -0.0000

Data Index: 2365 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.2314. Min Act: -0.0000

Data Index: 29869 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.0842. Min Act: -0.0000

Data Index: 724241 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 3.4776. Min Range: -3.4776

Max Act: 1.9566. Min Act: -0.0000

Data Index: 521230 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 3.4776. Min Range: -3.4776

Max Act: 2.0625. Min Act: -0.0000

Data Index: 393870 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 3.4776. Min Range: -3.4776

Max Act: 1.8302. Min Act: -0.0000

Data Index: 843488 (C4 (Web Text))

Max Activating Token Index: 236