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

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

Neuron 4919 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.9587. Min Act: -0.0000

Data Index: 1167399 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.5699. Min Act: -0.0000

Data Index: 95504 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.4929. Min Act: -0.0000

Data Index: 386241 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.3302. Min Act: -0.0000

Data Index: 7059 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.2020. Min Act: -0.0000

Data Index: 1537638 (Python Code)

Max Activating Token Index: 867

Text #5

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.2430. Min Act: -0.0000

Data Index: 605871 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.1976. Min Act: -0.0000

Data Index: 1372206 (Python Code)

Max Activating Token Index: 210

Text #7

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.1825. Min Act: -0.0000

Data Index: 1134595 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.0354. Min Act: -0.0000

Data Index: 205430 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.0420. Min Act: -0.0000

Data Index: 225058 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.1318. Min Act: -0.0000

Data Index: 1176848 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.0029. Min Act: -0.0000

Data Index: 106801 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.2138. Min Act: -0.0000

Data Index: 1395859 (Python Code)

Max Activating Token Index: 223

Text #13

Max Range: 2.9587. Min Range: -2.9587

Max Act: 1.9497. Min Act: -0.0000

Data Index: 622862 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.0212. Min Act: -0.0000

Data Index: 1443979 (Python Code)

Max Activating Token Index: 929

Text #15

Max Range: 2.9587. Min Range: -2.9587

Max Act: 1.9182. Min Act: -0.0000

Data Index: 182582 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 2.9587. Min Range: -2.9587

Max Act: 1.9924. Min Act: -0.0000

Data Index: 1020259 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 2.9587. Min Range: -2.9587

Max Act: 1.9525. Min Act: -0.0000

Data Index: 1606465 (Python Code)

Max Activating Token Index: 594

Text #18

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.0561. Min Act: -0.0000

Data Index: 497943 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.0367. Min Act: -0.0000

Data Index: 1496657 (Python Code)

Max Activating Token Index: 281