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

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

Neuron 2013 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.5837. Min Act: -0.0000

Data Index: 645537 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.5653. Min Act: -0.0000

Data Index: 704016 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.3684. Min Act: -0.0000

Data Index: 54841 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.2295. Min Act: -0.0000

Data Index: 264583 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.2843. Min Act: -0.0000

Data Index: 1054911 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.3948. Min Act: -0.0000

Data Index: 744937 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.2412. Min Act: -0.0001

Data Index: 368204 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.0650. Min Act: -0.0000

Data Index: 1061496 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.2104. Min Act: -0.0000

Data Index: 1330495 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.1047. Min Act: -0.0000

Data Index: 259063 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.1063. Min Act: -0.0000

Data Index: 213231 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.2641. Min Act: -0.0000

Data Index: 1054904 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.2403. Min Act: -0.0000

Data Index: 894064 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.2338. Min Act: -0.0000

Data Index: 944672 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.0832. Min Act: -0.0001

Data Index: 430918 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.0466. Min Act: -0.0001

Data Index: 31721 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.2384. Min Act: -0.0000

Data Index: 1131429 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.0327. Min Act: -0.0000

Data Index: 364467 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.8941. Min Act: -0.0001

Data Index: 524087 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.6041. Min Act: -0.0000

Data Index: 1329999 (C4 (Web Text))

Max Activating Token Index: 66