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

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

Neuron 2931 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0241. Min Range: -2.0241

Max Act: 2.0241. Min Act: -0.0000

Data Index: 714077 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.6697. Min Act: -0.0000

Data Index: 428220 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.5801. Min Act: -0.0000

Data Index: 1211130 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.6265. Min Act: -0.0000

Data Index: 1050765 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.4039. Min Act: -0.0000

Data Index: 275749 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.3458. Min Act: -0.0000

Data Index: 132461 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.3379. Min Act: -0.0000

Data Index: 1197871 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.3194. Min Act: -0.0000

Data Index: 620295 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.2866. Min Act: -0.0000

Data Index: 398718 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.1508. Min Act: -0.0000

Data Index: 1135337 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.2674. Min Act: -0.0000

Data Index: 1600363 (Python Code)

Max Activating Token Index: 114

Text #11

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.2282. Min Act: -0.0000

Data Index: 1238402 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.1786. Min Act: -0.0000

Data Index: 620573 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.1326. Min Act: -0.0000

Data Index: 1000787 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.1987. Min Act: -0.0000

Data Index: 442860 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.2268. Min Act: -0.0000

Data Index: 713989 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.0708. Min Act: -0.0000

Data Index: 376887 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.1476. Min Act: -0.0000

Data Index: 606245 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.0813. Min Act: -0.0000

Data Index: 268543 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 2.0241. Min Range: -2.0241

Max Act: 1.2114. Min Act: -0.0000

Data Index: 499469 (C4 (Web Text))

Max Activating Token Index: 724