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

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

Neuron 3391 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6838. Min Range: -2.6838

Max Act: 2.6838. Min Act: -0.0000

Data Index: 1342914 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 2.6838. Min Range: -2.6838

Max Act: 2.0706. Min Act: -0.0000

Data Index: 987462 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.9467. Min Act: -0.0000

Data Index: 457796 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.8498. Min Act: -0.0000

Data Index: 672477 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.7633. Min Act: -0.0000

Data Index: 21695 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.8432. Min Act: -0.0000

Data Index: 463147 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.7145. Min Act: -0.0000

Data Index: 273944 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.5620. Min Act: -0.0000

Data Index: 389065 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.4987. Min Act: -0.0000

Data Index: 211955 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.4144. Min Act: -0.0000

Data Index: 45731 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.5584. Min Act: -0.0000

Data Index: 154001 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.2807. Min Act: -0.0000

Data Index: 1265014 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.2357. Min Act: -0.0000

Data Index: 412359 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.3580. Min Act: -0.0000

Data Index: 298054 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.2636. Min Act: -0.0000

Data Index: 373515 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.1861. Min Act: -0.0000

Data Index: 855761 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.1842. Min Act: -0.0000

Data Index: 695869 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.1037. Min Act: -0.0000

Data Index: 303574 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1136178 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 2.6838. Min Range: -2.6838

Max Act: 1.1365. Min Act: -0.0000

Data Index: 743754 (C4 (Web Text))

Max Activating Token Index: 122