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

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

Neuron 1543 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.9374. Min Act: -0.0000

Data Index: 468303 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.8165. Min Act: -0.0000

Data Index: 497087 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.8360. Min Act: -0.0001

Data Index: 723901 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.6232. Min Act: -0.0001

Data Index: 34517 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.7918. Min Act: -0.0001

Data Index: 521913 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.7058. Min Act: -0.0000

Data Index: 897521 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.5252. Min Act: -0.0000

Data Index: 351969 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.5036. Min Act: -0.0001

Data Index: 383481 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.6493. Min Act: -0.0000

Data Index: 503868 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.6608. Min Act: -0.0001

Data Index: 529147 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.5822. Min Act: -0.0001

Data Index: 280128 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.4008. Min Act: -0.0000

Data Index: 253745 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.5813. Min Act: -0.0000

Data Index: 321695 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.7231. Min Act: -0.0001

Data Index: 277477 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.5393. Min Act: -0.0001

Data Index: 1098878 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.5323. Min Act: -0.0001

Data Index: 411433 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.3398. Min Act: -0.0000

Data Index: 541965 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.5288. Min Act: -0.0000

Data Index: 1074463 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.1503. Min Act: -0.0001

Data Index: 539222 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 4.9374. Min Range: -4.9374

Max Act: 4.6675. Min Act: -0.0001

Data Index: 1108332 (C4 (Web Text))

Max Activating Token Index: 228