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

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

Neuron 2162 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7683. Min Range: -5.7683

Max Act: 5.7683. Min Act: -0.0001

Data Index: 67504 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 5.7683. Min Range: -5.7683

Max Act: 4.7611. Min Act: -0.0001

Data Index: 1042032 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 5.7683. Min Range: -5.7683

Max Act: 4.7910. Min Act: -0.0001

Data Index: 1260475 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 5.7683. Min Range: -5.7683

Max Act: 4.3732. Min Act: -0.0000

Data Index: 755401 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 5.7683. Min Range: -5.7683

Max Act: 4.0041. Min Act: -0.0000

Data Index: 742945 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 5.7683. Min Range: -5.7683

Max Act: 4.1216. Min Act: -0.0000

Data Index: 386411 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 5.7683. Min Range: -5.7683

Max Act: 3.8975. Min Act: -0.0001

Data Index: 1245203 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 5.7683. Min Range: -5.7683

Max Act: 4.0156. Min Act: -0.0001

Data Index: 12822 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 5.7683. Min Range: -5.7683

Max Act: 4.0368. Min Act: -0.0000

Data Index: 316476 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 5.7683. Min Range: -5.7683

Max Act: 3.7756. Min Act: -0.0000

Data Index: 752660 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 5.7683. Min Range: -5.7683

Max Act: 3.8288. Min Act: -0.0001

Data Index: 585447 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 5.7683. Min Range: -5.7683

Max Act: 3.6491. Min Act: -0.0000

Data Index: 233170 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 5.7683. Min Range: -5.7683

Max Act: 3.5479. Min Act: -0.0001

Data Index: 642757 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 5.7683. Min Range: -5.7683

Max Act: 3.5096. Min Act: -0.0000

Data Index: 85424 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 5.7683. Min Range: -5.7683

Max Act: 3.7375. Min Act: -0.0001

Data Index: 737943 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 5.7683. Min Range: -5.7683

Max Act: 3.7164. Min Act: -0.0001

Data Index: 272820 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 5.7683. Min Range: -5.7683

Max Act: 3.5274. Min Act: -0.0001

Data Index: 675853 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 5.7683. Min Range: -5.7683

Max Act: 3.6251. Min Act: -0.0000

Data Index: 928028 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 5.7683. Min Range: -5.7683

Max Act: 3.6322. Min Act: -0.0001

Data Index: 397661 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 5.7683. Min Range: -5.7683

Max Act: 4.3647. Min Act: -0.0001

Data Index: 1295695 (C4 (Web Text))

Max Activating Token Index: 231