Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1347 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.9473. Min Act: -0.0000

Data Index: 221837 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.6924. Min Act: -0.0000

Data Index: 288428 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.7721. Min Act: -0.0000

Data Index: 299229 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.9468. Min Act: -0.0000

Data Index: 975862 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.6762. Min Act: -0.0000

Data Index: 1193259 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.6822. Min Act: -0.0000

Data Index: 444859 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.5676. Min Act: -0.0000

Data Index: 1457829 (Python Code)

Max Activating Token Index: 41

Text #7

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.5416. Min Act: -0.0000

Data Index: 332252 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.3879. Min Act: -0.0000

Data Index: 324718 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.5189. Min Act: -0.0000

Data Index: 1227045 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.4405. Min Act: -0.0000

Data Index: 436634 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.2944. Min Act: -0.0000

Data Index: 1437638 (Python Code)

Max Activating Token Index: 510

Text #12

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.3870. Min Act: -0.0000

Data Index: 984325 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.3251. Min Act: -0.0000

Data Index: 553994 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.3353. Min Act: -0.0000

Data Index: 1052503 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.3068. Min Act: -0.0000

Data Index: 800713 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.2766. Min Act: -0.0000

Data Index: 29628 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.2458. Min Act: -0.0000

Data Index: 790177 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.2449. Min Act: -0.0000

Data Index: 381343 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 2.9473. Min Range: -2.9473

Max Act: 2.1193. Min Act: -0.0000

Data Index: 145625 (C4 (Web Text))

Max Activating Token Index: 382