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

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

Neuron 3791 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0799. Min Range: -1.0799

Max Act: 1.0799. Min Act: -0.0003

Data Index: 782720 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 1.0799. Min Range: -1.0799

Max Act: 1.0053. Min Act: -0.0003

Data Index: 73253 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 1.0799. Min Range: -1.0799

Max Act: 1.0341. Min Act: -0.0003

Data Index: 1356634 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.9874. Min Act: -0.0003

Data Index: 608395 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.9291. Min Act: -0.0003

Data Index: 497889 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.9461. Min Act: -0.0003

Data Index: 880251 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.9137. Min Act: -0.0003

Data Index: 249943 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 1.0799. Min Range: -1.0799

Max Act: 1.0240. Min Act: -0.0003

Data Index: 829833 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.8212. Min Act: -0.0003

Data Index: 228274 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.9360. Min Act: -0.0003

Data Index: 125445 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.8804. Min Act: -0.0003

Data Index: 1334737 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.8765. Min Act: -0.0003

Data Index: 567152 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.8980. Min Act: -0.0003

Data Index: 1237718 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.8939. Min Act: -0.0003

Data Index: 1357797 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.7707. Min Act: -0.0003

Data Index: 189480 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.8147. Min Act: -0.0003

Data Index: 102787 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.8715. Min Act: -0.0004

Data Index: 146401 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.8280. Min Act: -0.0003

Data Index: 1130714 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.7988. Min Act: -0.0004

Data Index: 303092 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 1.0799. Min Range: -1.0799

Max Act: 0.7322. Min Act: -0.0003

Data Index: 1129478 (C4 (Web Text))

Max Activating Token Index: 650