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

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

Neuron 4820 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.4048. Min Act: 0.0000

Data Index: 1413165 (Python Code)

Max Activating Token Index: 992

Text #1

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.5586. Min Act: -0.0000

Data Index: 1576602 (Python Code)

Max Activating Token Index: 440

Text #2

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.4956. Min Act: 0.0000

Data Index: 1627118 (Python Code)

Max Activating Token Index: 144

Text #3

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.4499. Min Act: 0.0000

Data Index: 1436896 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.4944. Min Act: -0.0000

Data Index: 1530989 (Python Code)

Max Activating Token Index: 142

Text #5

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.3247. Min Act: -0.0000

Data Index: 1561280 (Python Code)

Max Activating Token Index: 853

Text #6

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.3311. Min Act: 0.0000

Data Index: 1485870 (Python Code)

Max Activating Token Index: 660

Text #7

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.2624. Min Act: 0.0000

Data Index: 1549318 (Python Code)

Max Activating Token Index: 163

Text #8

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.3233. Min Act: 0.0000

Data Index: 1578577 (Python Code)

Max Activating Token Index: 340

Text #9

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.2464. Min Act: -0.0000

Data Index: 1405083 (Python Code)

Max Activating Token Index: 91

Text #10

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1588898 (Python Code)

Max Activating Token Index: 1002

Text #11

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.1735. Min Act: -0.0000

Data Index: 1573348 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.1437. Min Act: 0.0000

Data Index: 615727 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1428013 (Python Code)

Max Activating Token Index: 388

Text #14

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.0129. Min Act: -0.0000

Data Index: 1547150 (Python Code)

Max Activating Token Index: 819

Text #15

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.0571. Min Act: -0.0000

Data Index: 1555324 (Python Code)

Max Activating Token Index: 340

Text #16

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.0617. Min Act: -0.0000

Data Index: 1501849 (Python Code)

Max Activating Token Index: 246

Text #17

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.0835. Min Act: -0.0000

Data Index: 1538502 (Python Code)

Max Activating Token Index: 723

Text #18

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1464246 (Python Code)

Max Activating Token Index: 777

Text #19

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1550358 (Python Code)

Max Activating Token Index: 218