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

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

Neuron 4244 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: 2.6853. Min Range: -2.6853

Max Act: 2.6629. Min Act: -0.0000

Data Index: 1317726 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.6853. Min Act: -0.0000

Data Index: 1227105 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.3889. Min Act: -0.0000

Data Index: 1184583 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.4411. Min Act: -0.0000

Data Index: 198220 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.4219. Min Act: -0.0000

Data Index: 588325 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.2970. Min Act: -0.0000

Data Index: 160167 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.2667. Min Act: -0.0000

Data Index: 948133 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.2246. Min Act: -0.0000

Data Index: 1262115 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.1296. Min Act: -0.0000

Data Index: 918403 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.0589. Min Act: -0.0000

Data Index: 509421 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.1772. Min Act: -0.0000

Data Index: 866544 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.2240. Min Act: -0.0000

Data Index: 1222441 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.0938. Min Act: -0.0000

Data Index: 500476 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.0372. Min Act: -0.0000

Data Index: 917670 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.2015. Min Act: -0.0000

Data Index: 213664 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 2.6853. Min Range: -2.6853

Max Act: 1.9954. Min Act: -0.0000

Data Index: 172220 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.1481. Min Act: -0.0000

Data Index: 107990 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.0829. Min Act: -0.0000

Data Index: 364046 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.0291. Min Act: -0.0000

Data Index: 220119 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 2.6853. Min Range: -2.6853

Max Act: 2.0361. Min Act: -0.0000

Data Index: 500960 (C4 (Web Text))

Max Activating Token Index: 311