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

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

Neuron 3964 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7648. Min Act: -0.0002

Data Index: 1601193 (Python Code)

Max Activating Token Index: 99

Text #1

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6356. Min Act: -0.0002

Data Index: 1563986 (Python Code)

Max Activating Token Index: 248

Text #2

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6208. Min Act: -0.0002

Data Index: 1394553 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6040. Min Act: -0.0002

Data Index: 1420949 (Python Code)

Max Activating Token Index: 141

Text #4

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.5930. Min Act: -0.0002

Data Index: 1475131 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6642. Min Act: -0.0002

Data Index: 1430298 (Python Code)

Max Activating Token Index: 94

Text #6

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.6474. Min Act: -0.0002

Data Index: 1549253 (Python Code)

Max Activating Token Index: 252

Text #7

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.3780. Min Act: -0.0002

Data Index: 1444119 (Python Code)

Max Activating Token Index: 209

Text #8

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.5416. Min Act: -0.0002

Data Index: 1612493 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.4867. Min Act: -0.0002

Data Index: 1553351 (Python Code)

Max Activating Token Index: 132

Text #10

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.4460. Min Act: -0.0002

Data Index: 1419763 (Python Code)

Max Activating Token Index: 333

Text #11

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.3724. Min Act: -0.0002

Data Index: 1588081 (Python Code)

Max Activating Token Index: 322

Text #12

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.4470. Min Act: -0.0002

Data Index: 1444319 (Python Code)

Max Activating Token Index: 198

Text #13

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.4183. Min Act: -0.0002

Data Index: 1502700 (Python Code)

Max Activating Token Index: 194

Text #14

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.4622. Min Act: -0.0002

Data Index: 1452370 (Python Code)

Max Activating Token Index: 296

Text #15

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.4477. Min Act: -0.0002

Data Index: 1426941 (Python Code)

Max Activating Token Index: 394

Text #16

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.4034. Min Act: -0.0002

Data Index: 1482340 (Python Code)

Max Activating Token Index: 519

Text #17

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.4380. Min Act: -0.0002

Data Index: 1584220 (Python Code)

Max Activating Token Index: 164

Text #18

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.3970. Min Act: -0.0002

Data Index: 1529065 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.3853. Min Act: -0.0002

Data Index: 1582580 (Python Code)

Max Activating Token Index: 383