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

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

Neuron 6090 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: 2.1537. Min Range: -2.1537

Max Act: 2.1537. Min Act: -0.0000

Data Index: 1084247 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.7967. Min Act: -0.0000

Data Index: 1301770 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.8755. Min Act: -0.0000

Data Index: 1165005 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.8998. Min Act: -0.0000

Data Index: 792739 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.7449. Min Act: -0.0000

Data Index: 617288 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.7000. Min Act: -0.0000

Data Index: 513625 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.7815. Min Act: -0.0000

Data Index: 73183 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.7502. Min Act: -0.0000

Data Index: 79077 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.6577. Min Act: -0.0000

Data Index: 731174 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.7063. Min Act: -0.0000

Data Index: 944988 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.7038. Min Act: -0.0000

Data Index: 175352 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.6056. Min Act: -0.0000

Data Index: 199079 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.6013. Min Act: -0.0000

Data Index: 1099715 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.6962. Min Act: -0.0000

Data Index: 242198 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.6858. Min Act: -0.0000

Data Index: 1185200 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.7868. Min Act: -0.0000

Data Index: 1047381 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.6632. Min Act: -0.0000

Data Index: 328802 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.5648. Min Act: -0.0000

Data Index: 1046781 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.6581. Min Act: -0.0000

Data Index: 305263 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 2.1537. Min Range: -2.1537

Max Act: 1.5649. Min Act: -0.0000

Data Index: 393687 (C4 (Web Text))

Max Activating Token Index: 88