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

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

Neuron 762 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.2209. Min Act: -0.0000

Data Index: 282332 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.2075. Min Act: -0.0000

Data Index: 698942 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1780. Min Act: -0.0000

Data Index: 675135 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1130302 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1956. Min Act: -0.0000

Data Index: 90403 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1853. Min Act: -0.0000

Data Index: 711207 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1784. Min Act: -0.0000

Data Index: 677405 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1659. Min Act: -0.0000

Data Index: 131330 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1518. Min Act: -0.0000

Data Index: 36483 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1607. Min Act: -0.0000

Data Index: 136900 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1616. Min Act: -0.0000

Data Index: 639332 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1396. Min Act: -0.0000

Data Index: 942156 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1363. Min Act: -0.0000

Data Index: 763664 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1556. Min Act: -0.0000

Data Index: 716601 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1109906 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1495. Min Act: -0.0000

Data Index: 504119 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1543. Min Act: -0.0000

Data Index: 1216143 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1523. Min Act: -0.0000

Data Index: 251888 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1157797 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1510. Min Act: -0.0000

Data Index: 928049 (C4 (Web Text))

Max Activating Token Index: 629