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

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

Neuron 357 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: 1.2730. Min Range: -1.2730

Max Act: 1.2730. Min Act: -0.0000

Data Index: 730207 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 1.2730. Min Range: -1.2730

Max Act: 1.1112. Min Act: -0.0000

Data Index: 506613 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 1.2730. Min Range: -1.2730

Max Act: 1.0634. Min Act: -0.0000

Data Index: 1323310 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 1.2730. Min Range: -1.2730

Max Act: 1.1339. Min Act: -0.0000

Data Index: 981940 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.9808. Min Act: -0.0000

Data Index: 521985 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.9842. Min Act: -0.0000

Data Index: 1201026 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.9589. Min Act: -0.0000

Data Index: 81797 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8944. Min Act: -0.0000

Data Index: 986348 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.9225. Min Act: -0.0000

Data Index: 478774 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8582. Min Act: -0.0000

Data Index: 611766 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8194. Min Act: -0.0000

Data Index: 554802 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1446342 (Python Code)

Max Activating Token Index: 297

Text #12

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8037. Min Act: -0.0000

Data Index: 197426 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8013. Min Act: -0.0000

Data Index: 354918 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.7730. Min Act: -0.0000

Data Index: 754210 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.7641. Min Act: -0.0000

Data Index: 1370147 (Python Code)

Max Activating Token Index: 489

Text #16

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.7678. Min Act: -0.0000

Data Index: 334337 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.7677. Min Act: -0.0000

Data Index: 973931 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.7472. Min Act: -0.0000

Data Index: 610909 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1181769 (C4 (Web Text))

Max Activating Token Index: 1022