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

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

Neuron 3176 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.6542. Min Act: -0.0000

Data Index: 31692 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1019200 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.6356. Min Act: -0.0000

Data Index: 717932 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1309830 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.6440. Min Act: -0.0000

Data Index: 236340 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1308852 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5612. Min Act: -0.0000

Data Index: 933678 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5584. Min Act: -0.0000

Data Index: 586471 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1190439 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5888. Min Act: -0.0000

Data Index: 630494 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5774. Min Act: -0.0000

Data Index: 723492 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5518. Min Act: -0.0000

Data Index: 220994 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1027666 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1085314 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5432. Min Act: -0.0000

Data Index: 611070 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5271. Min Act: -0.0000

Data Index: 117723 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1156284 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1426296 (Python Code)

Max Activating Token Index: 600

Text #18

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5271. Min Act: -0.0000

Data Index: 670499 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.6542. Min Range: -0.6542

Max Act: 0.5202. Min Act: -0.0000

Data Index: 30467 (C4 (Web Text))

Max Activating Token Index: 872