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

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

Neuron 4878 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0938. Min Range: -1.0938

Max Act: 1.0938. Min Act: -0.0000

Data Index: 334355 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 1.0938. Min Range: -1.0938

Max Act: 1.0106. Min Act: -0.0000

Data Index: 244761 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 1.0938. Min Range: -1.0938

Max Act: 1.0678. Min Act: -0.0000

Data Index: 99098 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 1.0938. Min Range: -1.0938

Max Act: 1.0491. Min Act: -0.0000

Data Index: 638638 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 1.0938. Min Range: -1.0938

Max Act: 1.0242. Min Act: -0.0000

Data Index: 727041 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 1.0938. Min Range: -1.0938

Max Act: 1.0835. Min Act: -0.0000

Data Index: 714371 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9489. Min Act: -0.0000

Data Index: 885774 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 1.0938. Min Range: -1.0938

Max Act: 1.0050. Min Act: -0.0000

Data Index: 984528 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1076620 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9125. Min Act: -0.0000

Data Index: 174749 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8605. Min Act: -0.0000

Data Index: 675688 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1251788 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1375046 (Python Code)

Max Activating Token Index: 1004

Text #13

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8380. Min Act: -0.0000

Data Index: 1354583 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.7759. Min Act: -0.0000

Data Index: 191627 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.7705. Min Act: -0.0000

Data Index: 981798 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1565866 (Python Code)

Max Activating Token Index: 524

Text #17

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.7104. Min Act: -0.0000

Data Index: 1280814 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.7420. Min Act: -0.0000

Data Index: 738019 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.7448. Min Act: -0.0000

Data Index: 691166 (C4 (Web Text))

Max Activating Token Index: 667