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

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

Neuron 3279 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: 2.5313. Min Range: -2.5313

Max Act: 2.5313. Min Act: 0.0000

Data Index: 395293 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 2.5313. Min Range: -2.5313

Max Act: 2.3529. Min Act: -0.0000

Data Index: 1172286 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 2.5313. Min Range: -2.5313

Max Act: 2.1251. Min Act: -0.0000

Data Index: 745408 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.9822. Min Act: 0.0002

Data Index: 375626 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.9783. Min Act: -0.0000

Data Index: 699416 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.9531. Min Act: 0.0002

Data Index: 502028 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.9352. Min Act: 0.0001

Data Index: 395396 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 2.5313. Min Range: -2.5313

Max Act: 2.0321. Min Act: -0.0000

Data Index: 462899 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.9667. Min Act: 0.0000

Data Index: 258976 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.8600. Min Act: -0.0000

Data Index: 837981 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.9300. Min Act: -0.0000

Data Index: 254124 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.8016. Min Act: -0.0000

Data Index: 1202170 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.7997. Min Act: -0.0000

Data Index: 593320 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.6685. Min Act: -0.0000

Data Index: 700413 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.6411. Min Act: -0.0000

Data Index: 287237 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.6556. Min Act: -0.0000

Data Index: 621214 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.5581. Min Act: -0.0000

Data Index: 660557 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.7016. Min Act: -0.0000

Data Index: 902914 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.6018. Min Act: -0.0000

Data Index: 886943 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 2.5313. Min Range: -2.5313

Max Act: 1.6002. Min Act: 0.0001

Data Index: 113320 (C4 (Web Text))

Max Activating Token Index: 985