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

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

Neuron 4419 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4822. Min Act: -0.0000

Data Index: 380182 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4824. Min Act: -0.0000

Data Index: 811025 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1245012 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4292. Min Act: -0.0000

Data Index: 531617 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4397. Min Act: -0.0000

Data Index: 406001 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1322551 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4613. Min Act: -0.0000

Data Index: 471077 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1085226 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4250. Min Act: -0.0000

Data Index: 369187 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4495. Min Act: -0.0000

Data Index: 822720 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4420. Min Act: -0.0000

Data Index: 137295 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1273745 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1174559 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1350927 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4043. Min Act: -0.0000

Data Index: 877418 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1194722 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1229318 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4009. Min Act: -0.0000

Data Index: 943966 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4077. Min Act: -0.0000

Data Index: 565082 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4116. Min Act: -0.0000

Data Index: 934262 (C4 (Web Text))

Max Activating Token Index: 528