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

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

Neuron 449 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.6834. Min Act: 0.0000

Data Index: 620643 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.6464. Min Act: -0.0000

Data Index: 412627 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.6284. Min Act: -0.0000

Data Index: 370031 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.6454. Min Act: -0.0000

Data Index: 1244261 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.6421. Min Act: -0.0000

Data Index: 656687 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5842. Min Act: -0.0000

Data Index: 338760 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5736. Min Act: -0.0000

Data Index: 704270 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1142264 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5700. Min Act: -0.0000

Data Index: 801348 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5324. Min Act: -0.0000

Data Index: 225933 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5412. Min Act: -0.0000

Data Index: 699442 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5087. Min Act: -0.0000

Data Index: 537992 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1230887 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5057. Min Act: 0.0001

Data Index: 1053305 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5135. Min Act: -0.0000

Data Index: 62881 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1148619 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4829. Min Act: -0.0000

Data Index: 60710 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4592. Min Act: -0.0000

Data Index: 424104 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4744. Min Act: -0.0000

Data Index: 420981 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4666. Min Act: 0.0002

Data Index: 638476 (C4 (Web Text))

Max Activating Token Index: 245