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

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

Neuron 2520 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: 1.4089. Min Range: -1.4089

Max Act: 1.4089. Min Act: -0.0000

Data Index: 837014 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.2908. Min Act: -0.0000

Data Index: 85299 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.2135. Min Act: -0.0000

Data Index: 36677 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.1239. Min Act: -0.0000

Data Index: 1110734 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.1044. Min Act: 0.0000

Data Index: 678250 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.0855. Min Act: -0.0000

Data Index: 734631 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.0894. Min Act: -0.0000

Data Index: 923724 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.0049. Min Act: -0.0000

Data Index: 200269 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 1.4089. Min Range: -1.4089

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1236595 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 1.4089. Min Range: -1.4089

Max Act: 0.9909. Min Act: -0.0000

Data Index: 888744 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 1.4089. Min Range: -1.4089

Max Act: 0.9889. Min Act: -0.0000

Data Index: 642275 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 1.4089. Min Range: -1.4089

Max Act: 0.9846. Min Act: -0.0000

Data Index: 61168 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 1.4089. Min Range: -1.4089

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1290175 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.0449. Min Act: -0.0000

Data Index: 1147878 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.0388. Min Act: -0.0000

Data Index: 778067 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 1.4089. Min Range: -1.4089

Max Act: 0.9630. Min Act: -0.0000

Data Index: 740248 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1295668 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 1.4089. Min Range: -1.4089

Max Act: 0.9129. Min Act: -0.0000

Data Index: 360784 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 1.4089. Min Range: -1.4089

Max Act: 0.8762. Min Act: -0.0000

Data Index: 598919 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 1.4089. Min Range: -1.4089

Max Act: 0.8816. Min Act: -0.0000

Data Index: 208544 (C4 (Web Text))

Max Activating Token Index: 348