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

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

Neuron 2731 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.2673. Min Act: -0.0000

Data Index: 1588260 (Python Code)

Max Activating Token Index: 34

Text #1

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.1400. Min Act: -0.0000

Data Index: 1480813 (Python Code)

Max Activating Token Index: 68

Text #2

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.9662. Min Act: -0.0000

Data Index: 1416102 (Python Code)

Max Activating Token Index: 965

Text #3

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.9394. Min Act: -0.0001

Data Index: 1493928 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.9406. Min Act: -0.0000

Data Index: 1566195 (Python Code)

Max Activating Token Index: 955

Text #5

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.7795. Min Act: -0.0000

Data Index: 1591706 (Python Code)

Max Activating Token Index: 150

Text #6

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.7372. Min Act: -0.0001

Data Index: 1648097 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.8174. Min Act: -0.0001

Data Index: 1498377 (Python Code)

Max Activating Token Index: 238

Text #8

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.7475. Min Act: -0.0000

Data Index: 1577067 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.5638. Min Act: -0.0000

Data Index: 1636938 (Python Code)

Max Activating Token Index: 114

Text #10

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.6862. Min Act: -0.0001

Data Index: 1561276 (Python Code)

Max Activating Token Index: 313

Text #11

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.6659. Min Act: -0.0001

Data Index: 1382786 (Python Code)

Max Activating Token Index: 226

Text #12

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.5192. Min Act: -0.0001

Data Index: 1560024 (Python Code)

Max Activating Token Index: 227

Text #13

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.4298. Min Act: -0.0001

Data Index: 1401879 (Python Code)

Max Activating Token Index: 594

Text #14

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.4974. Min Act: -0.0001

Data Index: 1478416 (Python Code)

Max Activating Token Index: 336

Text #15

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.5944. Min Act: -0.0000

Data Index: 1470398 (Python Code)

Max Activating Token Index: 76

Text #16

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.3145. Min Act: -0.0001

Data Index: 1378081 (Python Code)

Max Activating Token Index: 135

Text #17

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.7255. Min Act: -0.0001

Data Index: 1553726 (Python Code)

Max Activating Token Index: 108

Text #18

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.4425. Min Act: -0.0001

Data Index: 1484626 (Python Code)

Max Activating Token Index: 98

Text #19

Max Range: 3.2673. Min Range: -3.2673

Max Act: 2.5675. Min Act: -0.0000

Data Index: 1624931 (Python Code)

Max Activating Token Index: 48