Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 34 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3351. Min Act: -0.0001

Data Index: 1492317 (Python Code)

Max Activating Token Index: 22

Text #1

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2978. Min Act: -0.0001

Data Index: 1523369 (Python Code)

Max Activating Token Index: 1009

Text #2

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1582239 (Python Code)

Max Activating Token Index: 742

Text #3

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2409. Min Act: -0.0001

Data Index: 1569696 (Python Code)

Max Activating Token Index: 75

Text #4

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2392. Min Act: -0.0001

Data Index: 1569847 (Python Code)

Max Activating Token Index: 556

Text #5

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2316. Min Act: -0.0001

Data Index: 1647452 (Python Code)

Max Activating Token Index: 153

Text #6

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2182. Min Act: -0.0001

Data Index: 1495831 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2132. Min Act: -0.0001

Data Index: 1608169 (Python Code)

Max Activating Token Index: 875

Text #8

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2150. Min Act: -0.0001

Data Index: 1376353 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2017. Min Act: -0.0001

Data Index: 1360762 (Python Code)

Max Activating Token Index: 848

Text #10

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2152. Min Act: -0.0001

Data Index: 1565379 (Python Code)

Max Activating Token Index: 329

Text #11

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.1970. Min Act: -0.0001

Data Index: 1649044 (Python Code)

Max Activating Token Index: 738

Text #12

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1382740 (Python Code)

Max Activating Token Index: 531

Text #13

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2055. Min Act: -0.0001

Data Index: 1591187 (Python Code)

Max Activating Token Index: 375

Text #14

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2069. Min Act: -0.0001

Data Index: 1547579 (Python Code)

Max Activating Token Index: 187

Text #15

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2114. Min Act: -0.0001

Data Index: 1632184 (Python Code)

Max Activating Token Index: 763

Text #16

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2055. Min Act: -0.0001

Data Index: 1438337 (Python Code)

Max Activating Token Index: 647

Text #17

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.1962. Min Act: -0.0001

Data Index: 1400141 (Python Code)

Max Activating Token Index: 174

Text #18

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2085. Min Act: -0.0001

Data Index: 1360809 (Python Code)

Max Activating Token Index: 624

Text #19

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1530908 (Python Code)

Max Activating Token Index: 968