Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1928 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7220. Min Range: -1.7220

Max Act: 1.7220. Min Act: -0.0000

Data Index: 1419521 (Python Code)

Max Activating Token Index: 488

Text #1

Max Range: 1.7220. Min Range: -1.7220

Max Act: 1.5088. Min Act: -0.0000

Data Index: 1366974 (Python Code)

Max Activating Token Index: 344

Text #2

Max Range: 1.7220. Min Range: -1.7220

Max Act: 1.5775. Min Act: -0.0000

Data Index: 1583128 (Python Code)

Max Activating Token Index: 714

Text #3

Max Range: 1.7220. Min Range: -1.7220

Max Act: 1.5578. Min Act: -0.0000

Data Index: 1380617 (Python Code)

Max Activating Token Index: 410

Text #4

Max Range: 1.7220. Min Range: -1.7220

Max Act: 1.3643. Min Act: -0.0000

Data Index: 1454552 (Python Code)

Max Activating Token Index: 69

Text #5

Max Range: 1.7220. Min Range: -1.7220

Max Act: 1.3208. Min Act: -0.0000

Data Index: 1470752 (Python Code)

Max Activating Token Index: 206

Text #6

Max Range: 1.7220. Min Range: -1.7220

Max Act: 1.2851. Min Act: -0.0000

Data Index: 1482695 (Python Code)

Max Activating Token Index: 262

Text #7

Max Range: 1.7220. Min Range: -1.7220

Max Act: 1.2703. Min Act: -0.0000

Data Index: 1546666 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 1.7220. Min Range: -1.7220

Max Act: 1.2043. Min Act: -0.0000

Data Index: 1620149 (Python Code)

Max Activating Token Index: 546

Text #9

Max Range: 1.7220. Min Range: -1.7220

Max Act: 1.1089. Min Act: -0.0000

Data Index: 1572081 (Python Code)

Max Activating Token Index: 118

Text #10

Max Range: 1.7220. Min Range: -1.7220

Max Act: 1.0208. Min Act: -0.0000

Data Index: 234382 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 1.7220. Min Range: -1.7220

Max Act: 1.0078. Min Act: -0.0000

Data Index: 1422078 (Python Code)

Max Activating Token Index: 52

Text #12

Max Range: 1.7220. Min Range: -1.7220

Max Act: 0.9680. Min Act: -0.0000

Data Index: 148684 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 1.7220. Min Range: -1.7220

Max Act: 0.9702. Min Act: -0.0000

Data Index: 257393 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 1.7220. Min Range: -1.7220

Max Act: 0.9393. Min Act: -0.0000

Data Index: 711988 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 1.7220. Min Range: -1.7220

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1525453 (Python Code)

Max Activating Token Index: 423

Text #16

Max Range: 1.7220. Min Range: -1.7220

Max Act: 0.9155. Min Act: -0.0000

Data Index: 1263021 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 1.7220. Min Range: -1.7220

Max Act: 0.8771. Min Act: -0.0000

Data Index: 1304362 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.7220. Min Range: -1.7220

Max Act: 0.8723. Min Act: -0.0000

Data Index: 659195 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 1.7220. Min Range: -1.7220

Max Act: 0.7858. Min Act: -0.0000

Data Index: 200883 (C4 (Web Text))

Max Activating Token Index: 508