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

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

Neuron 4034 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: 0.6655. Min Range: -0.6655

Max Act: 0.6228. Min Act: -0.0000

Data Index: 759958 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6655. Min Act: -0.0000

Data Index: 781962 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6116. Min Act: -0.0000

Data Index: 99466 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5964. Min Act: -0.0000

Data Index: 913783 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1318413 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5736. Min Act: -0.0000

Data Index: 480553 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5669. Min Act: -0.0000

Data Index: 786603 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1016525 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5252. Min Act: -0.0000

Data Index: 775664 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5468. Min Act: -0.0000

Data Index: 920371 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5094. Min Act: -0.0000

Data Index: 152330 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5087. Min Act: -0.0000

Data Index: 240351 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1193988 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5234. Min Act: -0.0000

Data Index: 329236 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5023. Min Act: -0.0000

Data Index: 887722 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4794. Min Act: -0.0000

Data Index: 906670 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4945. Min Act: -0.0000

Data Index: 58233 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4785. Min Act: -0.0000

Data Index: 887261 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1095729 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1116610 (C4 (Web Text))

Max Activating Token Index: 159