Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1032 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.7554. Min Act: -0.0001

Data Index: 1138898 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.6253. Min Act: -0.0001

Data Index: 781160 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.6156. Min Act: -0.0001

Data Index: 933616 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.5769. Min Act: -0.0001

Data Index: 1061458 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.3778. Min Act: -0.0001

Data Index: 1050842 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.4789. Min Act: -0.0001

Data Index: 599457 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.4784. Min Act: -0.0001

Data Index: 140552 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.3715. Min Act: -0.0001

Data Index: 820606 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.3971. Min Act: -0.0001

Data Index: 742360 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.3870. Min Act: -0.0001

Data Index: 180156 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.3479. Min Act: -0.0001

Data Index: 464764 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.3685. Min Act: -0.0001

Data Index: 1018343 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.3756. Min Act: -0.0001

Data Index: 512786 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.3197. Min Act: -0.0001

Data Index: 187794 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.2414. Min Act: -0.0001

Data Index: 1095607 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.2731. Min Act: -0.0001

Data Index: 1372047 (Python Code)

Max Activating Token Index: 45

Text #16

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.2681. Min Act: -0.0001

Data Index: 516243 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.2499. Min Act: -0.0001

Data Index: 54869 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.2838. Min Act: -0.0001

Data Index: 860201 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 1.7554. Min Range: -1.7554

Max Act: 1.1818. Min Act: -0.0001

Data Index: 929099 (C4 (Web Text))

Max Activating Token Index: 105