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

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

Neuron 120 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.6260. Min Act: -0.0000

Data Index: 689343 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5728. Min Act: -0.0000

Data Index: 180498 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1196478 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5362. Min Act: -0.0000

Data Index: 181769 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5216. Min Act: -0.0000

Data Index: 439810 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4604. Min Act: -0.0000

Data Index: 168384 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1179090 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4321. Min Act: -0.0000

Data Index: 894406 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1126077 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4162. Min Act: -0.0000

Data Index: 490338 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4169. Min Act: -0.0000

Data Index: 94681 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1137799 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.3934. Min Act: -0.0000

Data Index: 103247 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.3987. Min Act: -0.0000

Data Index: 131313 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.3856. Min Act: -0.0000

Data Index: 870717 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.3814. Min Act: -0.0000

Data Index: 291224 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1283840 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1246219 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1284838 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.3612. Min Act: 0.0000

Data Index: 1003624 (C4 (Web Text))

Max Activating Token Index: 277