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

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

Neuron 4392 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5648. Min Range: -3.5648

Max Act: 3.5648. Min Act: -0.0000

Data Index: 1238134 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 3.5648. Min Range: -3.5648

Max Act: 3.3327. Min Act: -0.0000

Data Index: 277324 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 3.5648. Min Range: -3.5648

Max Act: 2.8697. Min Act: -0.0000

Data Index: 235529 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 3.5648. Min Range: -3.5648

Max Act: 3.1229. Min Act: -0.0000

Data Index: 1241314 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 3.5648. Min Range: -3.5648

Max Act: 3.1126. Min Act: -0.0000

Data Index: 463988 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 3.5648. Min Range: -3.5648

Max Act: 3.0239. Min Act: -0.0000

Data Index: 915703 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 3.5648. Min Range: -3.5648

Max Act: 2.8314. Min Act: -0.0000

Data Index: 492854 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 3.5648. Min Range: -3.5648

Max Act: 3.1003. Min Act: -0.0000

Data Index: 355605 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 3.5648. Min Range: -3.5648

Max Act: 3.3550. Min Act: -0.0000

Data Index: 1261323 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 3.5648. Min Range: -3.5648

Max Act: 2.8852. Min Act: -0.0000

Data Index: 193842 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 3.5648. Min Range: -3.5648

Max Act: 2.8188. Min Act: -0.0000

Data Index: 921803 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 3.5648. Min Range: -3.5648

Max Act: 2.6870. Min Act: -0.0000

Data Index: 335847 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 3.5648. Min Range: -3.5648

Max Act: 3.0991. Min Act: -0.0000

Data Index: 737268 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 3.5648. Min Range: -3.5648

Max Act: 2.8074. Min Act: -0.0000

Data Index: 1035736 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 3.5648. Min Range: -3.5648

Max Act: 2.9366. Min Act: -0.0000

Data Index: 74723 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 3.5648. Min Range: -3.5648

Max Act: 2.7745. Min Act: -0.0000

Data Index: 691523 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 3.5648. Min Range: -3.5648

Max Act: 2.7515. Min Act: -0.0000

Data Index: 1150229 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 3.5648. Min Range: -3.5648

Max Act: 2.7466. Min Act: -0.0001

Data Index: 581556 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 3.5648. Min Range: -3.5648

Max Act: 2.6847. Min Act: -0.0000

Data Index: 64563 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 3.5648. Min Range: -3.5648

Max Act: 2.6898. Min Act: -0.0001

Data Index: 89801 (C4 (Web Text))

Max Activating Token Index: 1010