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

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

Neuron 667 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.8438. Min Act: -0.0000

Data Index: 1515760 (Python Code)

Max Activating Token Index: 191

Text #1

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.7973. Min Act: -0.0000

Data Index: 1543969 (Python Code)

Max Activating Token Index: 533

Text #2

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.7359. Min Act: -0.0000

Data Index: 1371843 (Python Code)

Max Activating Token Index: 210

Text #3

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.7754. Min Act: -0.0000

Data Index: 1371838 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.7122. Min Act: -0.0000

Data Index: 1394851 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.6138. Min Act: -0.0000

Data Index: 1570796 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.5104. Min Act: -0.0000

Data Index: 1543006 (Python Code)

Max Activating Token Index: 16

Text #7

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.4938. Min Act: -0.0000

Data Index: 1575066 (Python Code)

Max Activating Token Index: 116

Text #8

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.4668. Min Act: -0.0000

Data Index: 1522326 (Python Code)

Max Activating Token Index: 576

Text #9

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.4861. Min Act: -0.0000

Data Index: 1472920 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.4455. Min Act: -0.0000

Data Index: 1415412 (Python Code)

Max Activating Token Index: 50

Text #11

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.3979. Min Act: -0.0000

Data Index: 1457043 (Python Code)

Max Activating Token Index: 60

Text #12

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.4873. Min Act: -0.0000

Data Index: 1417787 (Python Code)

Max Activating Token Index: 285

Text #13

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.2376. Min Act: -0.0000

Data Index: 1383791 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.3057. Min Act: -0.0000

Data Index: 1413752 (Python Code)

Max Activating Token Index: 69

Text #15

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.3667. Min Act: -0.0000

Data Index: 1574276 (Python Code)

Max Activating Token Index: 582

Text #16

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.3635. Min Act: -0.0000

Data Index: 1585494 (Python Code)

Max Activating Token Index: 782

Text #17

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.2468. Min Act: -0.0000

Data Index: 1647904 (Python Code)

Max Activating Token Index: 268

Text #18

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.5724. Min Act: -0.0000

Data Index: 1489299 (Python Code)

Max Activating Token Index: 158

Text #19

Max Range: 1.8438. Min Range: -1.8438

Max Act: 1.3266. Min Act: -0.0000

Data Index: 1383078 (Python Code)

Max Activating Token Index: 60