Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 289 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.4751. Min Act: -0.0000

Data Index: 248567 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3770. Min Act: -0.0000

Data Index: 611990 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3697. Min Act: 0.0000

Data Index: 161502 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3596. Min Act: -0.0000

Data Index: 20024 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3690. Min Act: -0.0000

Data Index: 495868 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1319614 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3491. Min Act: -0.0000

Data Index: 63108 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3115. Min Act: -0.0000

Data Index: 411558 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1036642 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3027. Min Act: -0.0000

Data Index: 270277 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1273351 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1081884 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.2809. Min Act: 0.0000

Data Index: 966507 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.2673. Min Act: -0.0000

Data Index: 416743 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.2659. Min Act: -0.0000

Data Index: 6761 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1326660 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.2641. Min Act: -0.0000

Data Index: 303510 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1181737 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1216491 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.2569. Min Act: -0.0000

Data Index: 592768 (C4 (Web Text))

Max Activating Token Index: 619