Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3397 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.2968. Min Act: -0.0001

Data Index: 332882 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.3609. Min Act: -0.0001

Data Index: 1123207 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.0748. Min Act: -0.0001

Data Index: 881870 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.0570. Min Act: -0.0001

Data Index: 308895 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.2116. Min Act: -0.0001

Data Index: 849314 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.1765. Min Act: -0.0001

Data Index: 180236 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.1142. Min Act: -0.0001

Data Index: 676871 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.0101. Min Act: -0.0001

Data Index: 121855 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.0414. Min Act: -0.0001

Data Index: 86322 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.0259. Min Act: -0.0001

Data Index: 370604 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9718. Min Act: -0.0001

Data Index: 617968 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9851. Min Act: -0.0001

Data Index: 32251 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9473. Min Act: -0.0001

Data Index: 832330 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.8669. Min Act: -0.0001

Data Index: 415831 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.8983. Min Act: -0.0001

Data Index: 310312 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9314. Min Act: -0.0001

Data Index: 1382 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9416. Min Act: -0.0001

Data Index: 1056712 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.0770. Min Act: -0.0001

Data Index: 554196 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.8917. Min Act: -0.0001

Data Index: 172279 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9739. Min Act: -0.0001

Data Index: 1298825 (C4 (Web Text))

Max Activating Token Index: 894