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

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

Neuron 2909 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: 0.4789. Min Range: -0.4789

Max Act: 0.4496. Min Act: -0.0000

Data Index: 10564 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4789. Min Act: -0.0000

Data Index: 720391 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4412. Min Act: -0.0000

Data Index: 29844 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3925. Min Act: -0.0000

Data Index: 411282 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3739. Min Act: 0.0000

Data Index: 197615 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3827. Min Act: -0.0000

Data Index: 537872 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3901. Min Act: -0.0000

Data Index: 743186 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3802. Min Act: -0.0000

Data Index: 4957 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3674. Min Act: -0.0000

Data Index: 268734 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1092347 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3470. Min Act: -0.0000

Data Index: 645807 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3543. Min Act: -0.0000

Data Index: 737438 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3538. Min Act: -0.0000

Data Index: 672785 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3305. Min Act: -0.0000

Data Index: 749054 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3411. Min Act: -0.0000

Data Index: 944292 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3474. Min Act: -0.0000

Data Index: 897558 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3221. Min Act: -0.0000

Data Index: 404831 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1328825 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3280. Min Act: 0.0000

Data Index: 1147672 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3326. Min Act: -0.0000

Data Index: 888280 (C4 (Web Text))

Max Activating Token Index: 930