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

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

Neuron 4404 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5596. Min Range: -2.5596

Max Act: 2.5596. Min Act: -0.0000

Data Index: 1114911 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 2.5596. Min Range: -2.5596

Max Act: 2.0944. Min Act: -0.0000

Data Index: 1024901 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.9669. Min Act: -0.0000

Data Index: 729381 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.9304. Min Act: -0.0000

Data Index: 870407 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.9857. Min Act: -0.0000

Data Index: 1098829 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.7992. Min Act: -0.0000

Data Index: 613025 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.7907. Min Act: -0.0000

Data Index: 960218 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.8829. Min Act: -0.0000

Data Index: 305925 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.7542. Min Act: -0.0000

Data Index: 799384 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.7858. Min Act: -0.0000

Data Index: 1106239 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.8554. Min Act: -0.0000

Data Index: 342802 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.7294. Min Act: -0.0000

Data Index: 1334420 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.9275. Min Act: -0.0000

Data Index: 326424 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.8015. Min Act: -0.0000

Data Index: 1161929 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.6630. Min Act: -0.0000

Data Index: 658655 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.7174. Min Act: -0.0000

Data Index: 517618 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.7248. Min Act: -0.0000

Data Index: 939615 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.4145. Min Act: -0.0000

Data Index: 229315 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.6916. Min Act: -0.0000

Data Index: 265389 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 2.5596. Min Range: -2.5596

Max Act: 1.6973. Min Act: -0.0000

Data Index: 32088 (C4 (Web Text))

Max Activating Token Index: 386