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

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

Neuron 3391 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4499. Min Act: -0.0001

Data Index: 440462 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4181. Min Act: -0.0001

Data Index: 997829 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4601. Min Act: -0.0001

Data Index: 436598 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4596. Min Act: -0.0001

Data Index: 1006179 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4445. Min Act: -0.0001

Data Index: 230498 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.3938. Min Act: -0.0001

Data Index: 264393 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4180. Min Act: -0.0001

Data Index: 65425 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4248. Min Act: -0.0001

Data Index: 464028 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4371. Min Act: -0.0001

Data Index: 821004 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4163. Min Act: -0.0001

Data Index: 886227 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.3982. Min Act: -0.0001

Data Index: 1338455 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.3722. Min Act: -0.0001

Data Index: 997648 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4217. Min Act: -0.0001

Data Index: 64338 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.3949. Min Act: -0.0001

Data Index: 130481 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.3826. Min Act: -0.0001

Data Index: 55452 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4245. Min Act: -0.0001

Data Index: 81320 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.3683. Min Act: -0.0001

Data Index: 1336506 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4068. Min Act: -0.0001

Data Index: 642827 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.3899. Min Act: -0.0001

Data Index: 1205090 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.4601. Min Range: -0.4601

Max Act: 0.4019. Min Act: -0.0001

Data Index: 193990 (C4 (Web Text))

Max Activating Token Index: 837