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

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

Neuron 4207 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.9557. Min Act: -0.0000

Data Index: 482407 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.9589. Min Act: -0.0000

Data Index: 483825 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.9546. Min Act: -0.0000

Data Index: 265579 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.7810. Min Act: -0.0000

Data Index: 73602 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.8520. Min Act: -0.0000

Data Index: 855373 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.7787. Min Act: -0.0000

Data Index: 11877 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.7759. Min Act: -0.0000

Data Index: 344970 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1320368 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.7731. Min Act: -0.0000

Data Index: 730624 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.7664. Min Act: -0.0000

Data Index: 873263 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1166510 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.7176. Min Act: -0.0000

Data Index: 340957 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.7620. Min Act: -0.0000

Data Index: 518346 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1011121 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.7139. Min Act: 0.0000

Data Index: 1195490 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.6844. Min Act: -0.0000

Data Index: 543549 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.7162. Min Act: -0.0000

Data Index: 462353 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.6628. Min Act: -0.0000

Data Index: 115167 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1024968 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.9589. Min Range: -0.9589

Max Act: 0.6201. Min Act: -0.0000

Data Index: 48122 (C4 (Web Text))

Max Activating Token Index: 338