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

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

Neuron 695 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.8345. Min Act: -0.0000

Data Index: 1339862 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.8263. Min Act: -0.0000

Data Index: 1071408 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.7512. Min Act: -0.0000

Data Index: 1325702 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.7042. Min Act: -0.0000

Data Index: 931906 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.6397. Min Act: -0.0000

Data Index: 865299 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.4430. Min Act: -0.0000

Data Index: 1141526 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.3924. Min Act: -0.0000

Data Index: 158392 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.2664. Min Act: -0.0000

Data Index: 487040 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.4387. Min Act: -0.0000

Data Index: 924700 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.3987. Min Act: -0.0000

Data Index: 912460 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.1179. Min Act: -0.0000

Data Index: 588420 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.3528. Min Act: -0.0000

Data Index: 670039 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 2.8345. Min Range: -2.8345

Max Act: 1.9507. Min Act: -0.0000

Data Index: 49277 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.1560. Min Act: -0.0000

Data Index: 97108 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.0080. Min Act: -0.0000

Data Index: 1352111 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.1099. Min Act: -0.0000

Data Index: 995125 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.1016. Min Act: -0.0000

Data Index: 929356 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.0927. Min Act: -0.0000

Data Index: 801494 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 2.8345. Min Range: -2.8345

Max Act: 2.0644. Min Act: -0.0000

Data Index: 304011 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 2.8345. Min Range: -2.8345

Max Act: 1.7906. Min Act: -0.0000

Data Index: 12187 (C4 (Web Text))

Max Activating Token Index: 784