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

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

Neuron 3322 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.3091. Min Act: -0.0000

Data Index: 1510334 (Python Code)

Max Activating Token Index: 583

Text #1

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1509927 (Python Code)

Max Activating Token Index: 835

Text #2

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1603602 (Python Code)

Max Activating Token Index: 1021

Text #3

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.1035. Min Act: -0.0000

Data Index: 1593814 (Python Code)

Max Activating Token Index: 992

Text #4

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1427185 (Python Code)

Max Activating Token Index: 305

Text #5

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1444615 (Python Code)

Max Activating Token Index: 615

Text #6

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1523065 (Python Code)

Max Activating Token Index: 735

Text #7

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1411675 (Python Code)

Max Activating Token Index: 853

Text #8

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.8587. Min Act: -0.0000

Data Index: 1531294 (Python Code)

Max Activating Token Index: 708

Text #9

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1529006 (Python Code)

Max Activating Token Index: 925

Text #10

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.7541. Min Act: -0.0000

Data Index: 1558185 (Python Code)

Max Activating Token Index: 937

Text #11

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.8145. Min Act: -0.0000

Data Index: 1634274 (Python Code)

Max Activating Token Index: 791

Text #12

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1536436 (Python Code)

Max Activating Token Index: 840

Text #13

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1556670 (Python Code)

Max Activating Token Index: 895

Text #14

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.7128. Min Act: -0.0000

Data Index: 1415859 (Python Code)

Max Activating Token Index: 883

Text #15

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.7063. Min Act: -0.0000

Data Index: 1412262 (Python Code)

Max Activating Token Index: 276

Text #16

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.7690. Min Act: -0.0000

Data Index: 1451660 (Python Code)

Max Activating Token Index: 914

Text #17

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1493201 (Python Code)

Max Activating Token Index: 461

Text #18

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1515101 (Python Code)

Max Activating Token Index: 291

Text #19

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.7601. Min Act: -0.0000

Data Index: 1597718 (Python Code)

Max Activating Token Index: 54