Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1057 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.6655. Min Act: -0.0000

Data Index: 151575 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.5159. Min Act: -0.0000

Data Index: 1107535 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.4140. Min Act: -0.0000

Data Index: 508066 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.2717. Min Act: -0.0000

Data Index: 503189 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.3378. Min Act: -0.0000

Data Index: 130446 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.7738. Min Act: -0.0000

Data Index: 846243 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.8484. Min Act: -0.0000

Data Index: 921031 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.9845. Min Act: -0.0000

Data Index: 458586 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.9445. Min Act: -0.0000

Data Index: 205669 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.7755. Min Act: -0.0000

Data Index: 214490 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 3.6655. Min Range: -3.6655

Max Act: 3.0063. Min Act: -0.0000

Data Index: 67431 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.9984. Min Act: -0.0000

Data Index: 803372 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.8614. Min Act: -0.0000

Data Index: 884707 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.6965. Min Act: -0.0000

Data Index: 132173 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.8199. Min Act: -0.0000

Data Index: 3025 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.8158. Min Act: -0.0000

Data Index: 454362 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.8021. Min Act: -0.0000

Data Index: 312354 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.6592. Min Act: -0.0000

Data Index: 1198331 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.7669. Min Act: -0.0000

Data Index: 583820 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 3.6655. Min Range: -3.6655

Max Act: 2.7496. Min Act: -0.0000

Data Index: 1347806 (C4 (Web Text))

Max Activating Token Index: 70