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

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

Neuron 298 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1284914 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8496. Min Act: -0.0000

Data Index: 270084 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1044586 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8848. Min Act: -0.0000

Data Index: 322826 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8293. Min Act: -0.0000

Data Index: 1038518 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8205. Min Act: -0.0000

Data Index: 306416 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7823. Min Act: -0.0000

Data Index: 773336 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7755. Min Act: -0.0000

Data Index: 558562 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7759. Min Act: -0.0000

Data Index: 889485 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7505. Min Act: -0.0000

Data Index: 385737 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7938. Min Act: -0.0000

Data Index: 690248 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7708. Min Act: -0.0000

Data Index: 639423 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7370. Min Act: -0.0000

Data Index: 665734 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7557. Min Act: -0.0000

Data Index: 609809 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7331. Min Act: -0.0000

Data Index: 169305 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7592. Min Act: -0.0000

Data Index: 86076 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7482. Min Act: -0.0000

Data Index: 230886 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7218. Min Act: -0.0000

Data Index: 522008 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1014685 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7420. Min Act: -0.0000

Data Index: 152070 (C4 (Web Text))

Max Activating Token Index: 169