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

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

Neuron 1452 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1865. Min Act: -0.0001

Data Index: 811543 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1748. Min Act: -0.0001

Data Index: 291961 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1614. Min Act: -0.0001

Data Index: 1293483 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1562. Min Act: -0.0001

Data Index: 569296 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1490. Min Act: -0.0001

Data Index: 317157 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1494. Min Act: -0.0001

Data Index: 901749 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1341. Min Act: -0.0001

Data Index: 146347 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1149611 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1250. Min Act: -0.0001

Data Index: 760593 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1314. Min Act: -0.0001

Data Index: 210105 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1325. Min Act: -0.0001

Data Index: 857356 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1170. Min Act: -0.0001

Data Index: 12668 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1543013 (Python Code)

Max Activating Token Index: 464

Text #13

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1190. Min Act: -0.0001

Data Index: 857860 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1177911 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1003. Min Act: -0.0001

Data Index: 191218 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1105. Min Act: -0.0001

Data Index: 569002 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1124. Min Act: -0.0001

Data Index: 21080 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1001. Min Act: -0.0001

Data Index: 917011 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1549939 (Python Code)

Max Activating Token Index: 184