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

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

Neuron 144 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.7578. Min Act: -0.0000

Data Index: 822733 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.7707. Min Act: -0.0000

Data Index: 551839 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.5195. Min Act: -0.0000

Data Index: 951249 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.5201. Min Act: -0.0000

Data Index: 1256305 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.6367. Min Act: -0.0000

Data Index: 1048823 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.4470. Min Act: -0.0000

Data Index: 818757 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.5376. Min Act: -0.0000

Data Index: 582593 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.5283. Min Act: -0.0000

Data Index: 1257244 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.5306. Min Act: -0.0000

Data Index: 618849 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.5036. Min Act: -0.0000

Data Index: 1116542 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.4669. Min Act: -0.0000

Data Index: 471252 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.3723. Min Act: -0.0000

Data Index: 396513 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.3705. Min Act: -0.0000

Data Index: 509519 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.0725. Min Act: -0.0000

Data Index: 1001514 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.2870. Min Act: -0.0000

Data Index: 573455 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.2935. Min Act: -0.0000

Data Index: 111904 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.2429. Min Act: -0.0000

Data Index: 865387 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.0870. Min Act: -0.0000

Data Index: 907739 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.1261. Min Act: -0.0000

Data Index: 1015705 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 2.7707. Min Range: -2.7707

Max Act: 2.2643. Min Act: -0.0000

Data Index: 924147 (C4 (Web Text))

Max Activating Token Index: 576