Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3029 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.1285. Min Act: -0.0001

Data Index: 630429 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0445. Min Act: -0.0001

Data Index: 885696 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0548. Min Act: -0.0001

Data Index: 108111 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0478. Min Act: -0.0001

Data Index: 117317 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0583. Min Act: -0.0001

Data Index: 193651 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0282. Min Act: -0.0001

Data Index: 983622 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0007. Min Act: -0.0001

Data Index: 72476 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9727. Min Act: -0.0001

Data Index: 987751 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0352. Min Act: -0.0001

Data Index: 127535 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0336. Min Act: -0.0001

Data Index: 1146192 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9984. Min Act: -0.0001

Data Index: 1295328 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0322. Min Act: -0.0001

Data Index: 672648 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9663. Min Act: -0.0001

Data Index: 887574 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9751. Min Act: -0.0001

Data Index: 1203366 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9635. Min Act: -0.0001

Data Index: 1097322 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0247. Min Act: -0.0001

Data Index: 403128 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9889. Min Act: -0.0001

Data Index: 1020722 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0140. Min Act: -0.0001

Data Index: 1126628 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9770. Min Act: -0.0001

Data Index: 380488 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9508. Min Act: -0.0001

Data Index: 1138215 (C4 (Web Text))

Max Activating Token Index: 256