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

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

Neuron 1439 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1447. Min Act: -0.0000

Data Index: 136718 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1219. Min Act: -0.0000

Data Index: 131378 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1499761 (Python Code)

Max Activating Token Index: 261

Text #3

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1328370 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1540262 (Python Code)

Max Activating Token Index: 306

Text #5

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1574124 (Python Code)

Max Activating Token Index: 250

Text #6

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1073227 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1107. Min Act: -0.0000

Data Index: 164850 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1089. Min Act: -0.0000

Data Index: 326146 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1414663 (Python Code)

Max Activating Token Index: 192

Text #10

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.0949. Min Act: -0.0001

Data Index: 1560244 (Python Code)

Max Activating Token Index: 434

Text #11

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1427609 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.0917. Min Act: -0.0000

Data Index: 766715 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.0874. Min Act: -0.0001

Data Index: 1579264 (Python Code)

Max Activating Token Index: 213

Text #14

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.0800. Min Act: -0.0000

Data Index: 506867 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1289457 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.0842. Min Act: -0.0000

Data Index: 171115 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.0820. Min Act: -0.0001

Data Index: 1579521 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.0787. Min Act: -0.0000

Data Index: 790080 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.0836. Min Act: -0.0000

Data Index: 794958 (C4 (Web Text))

Max Activating Token Index: 492