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

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

Neuron 3171 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0513. Min Range: -1.0513

Max Act: 1.0513. Min Act: -0.0000

Data Index: 598498 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.8144. Min Act: -0.0000

Data Index: 904081 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.7112. Min Act: -0.0000

Data Index: 50098 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.6872. Min Act: -0.0000

Data Index: 757130 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1065388 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.6481. Min Act: -0.0000

Data Index: 885065 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.6481. Min Act: -0.0000

Data Index: 943919 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.6416. Min Act: -0.0000

Data Index: 687631 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.6131. Min Act: -0.0000

Data Index: 435720 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.6028. Min Act: -0.0000

Data Index: 546252 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1055891 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1270520 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.6263. Min Act: -0.0000

Data Index: 509439 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1049385 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.5293. Min Act: -0.0000

Data Index: 35245 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.5911. Min Act: -0.0000

Data Index: 601757 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.5708. Min Act: -0.0000

Data Index: 604955 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.5645. Min Act: -0.0000

Data Index: 845830 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1345818 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 1.0513. Min Range: -1.0513

Max Act: 0.5882. Min Act: -0.0000

Data Index: 103719 (C4 (Web Text))

Max Activating Token Index: 495