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

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

Neuron 6027 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0714. Min Range: -2.0714

Max Act: 2.0714. Min Act: -0.0000

Data Index: 675751 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 2.0714. Min Range: -2.0714

Max Act: 2.0271. Min Act: -0.0000

Data Index: 331198 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.8819. Min Act: -0.0000

Data Index: 1117664 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.9709. Min Act: -0.0000

Data Index: 1090749 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.9144. Min Act: -0.0000

Data Index: 1080574 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.8094. Min Act: -0.0000

Data Index: 1235760 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.9022. Min Act: -0.0000

Data Index: 870784 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.7889. Min Act: -0.0000

Data Index: 227724 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.7830. Min Act: -0.0000

Data Index: 1138198 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.8485. Min Act: -0.0000

Data Index: 1231431 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.8301. Min Act: -0.0000

Data Index: 1094081 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.8288. Min Act: -0.0000

Data Index: 868942 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.7177. Min Act: -0.0000

Data Index: 774211 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.7880. Min Act: -0.0000

Data Index: 940987 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.8699. Min Act: -0.0000

Data Index: 755086 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.6733. Min Act: -0.0000

Data Index: 402291 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.7604. Min Act: -0.0000

Data Index: 48780 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.7465. Min Act: -0.0000

Data Index: 261818 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.6287. Min Act: -0.0000

Data Index: 750347 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 2.0714. Min Range: -2.0714

Max Act: 1.7276. Min Act: -0.0000

Data Index: 1410161 (Python Code)

Max Activating Token Index: 794