Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 610 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.4051. Min Act: -0.0003

Data Index: 840219 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3718. Min Act: -0.0003

Data Index: 72048 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3627. Min Act: -0.0003

Data Index: 656320 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3823. Min Act: -0.0003

Data Index: 307447 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3782. Min Act: -0.0003

Data Index: 1253332 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3652. Min Act: -0.0003

Data Index: 1349301 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3424. Min Act: -0.0003

Data Index: 491683 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3742. Min Act: -0.0003

Data Index: 618327 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3716. Min Act: -0.0003

Data Index: 516182 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3591. Min Act: -0.0003

Data Index: 267673 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3221. Min Act: -0.0003

Data Index: 253002 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3526. Min Act: -0.0003

Data Index: 222256 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3348. Min Act: -0.0003

Data Index: 1146549 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3041. Min Act: -0.0003

Data Index: 651918 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3445. Min Act: -0.0003

Data Index: 1123718 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3306. Min Act: -0.0003

Data Index: 116481 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3427. Min Act: -0.0003

Data Index: 810957 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3289. Min Act: -0.0003

Data Index: 788233 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.2939. Min Act: -0.0003

Data Index: 1148882 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.2841. Min Act: -0.0003

Data Index: 81847 (C4 (Web Text))

Max Activating Token Index: 621