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

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

Neuron 4015 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.7856. Min Act: -0.0001

Data Index: 297173 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.8000. Min Act: -0.0001

Data Index: 25373 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.8000. Min Act: -0.0001

Data Index: 595569 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.8000. Min Act: -0.0001

Data Index: 1105209 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.7461. Min Act: -0.0001

Data Index: 157289 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.6942. Min Act: -0.0001

Data Index: 449785 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.0234. Min Act: -0.0001

Data Index: 319460 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.5368. Min Act: -0.0001

Data Index: 29874 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.0559. Min Act: -0.0001

Data Index: 134094 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.4430. Min Act: -0.0001

Data Index: 930024 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.1845. Min Act: -0.0001

Data Index: 283125 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.3453. Min Act: -0.0001

Data Index: 1330232 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.0982. Min Act: -0.0001

Data Index: 620773 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.1995. Min Act: -0.0001

Data Index: 988133 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.0801. Min Act: -0.0001

Data Index: 931842 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 5.8000. Min Range: -5.8000

Max Act: 4.8562. Min Act: -0.0001

Data Index: 404221 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 5.8000. Min Range: -5.8000

Max Act: 3.9178. Min Act: -0.0001

Data Index: 1188274 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 5.8000. Min Range: -5.8000

Max Act: 5.2445. Min Act: -0.0001

Data Index: 561910 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 5.8000. Min Range: -5.8000

Max Act: 4.8567. Min Act: -0.0001

Data Index: 833898 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 5.8000. Min Range: -5.8000

Max Act: 4.5283. Min Act: -0.0001

Data Index: 881697 (C4 (Web Text))

Max Activating Token Index: 146