Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3236 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1632081 (Python Code)

Max Activating Token Index: 27

Text #1

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0931. Min Act: -0.0001

Data Index: 1584578 (Python Code)

Max Activating Token Index: 930

Text #2

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0904. Min Act: -0.0001

Data Index: 603099 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0871. Min Act: -0.0002

Data Index: 231812 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0920. Min Act: -0.0001

Data Index: 1271637 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0894. Min Act: -0.0001

Data Index: 324668 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0870. Min Act: -0.0001

Data Index: 48421 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0905. Min Act: -0.0002

Data Index: 752678 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0875. Min Act: -0.0001

Data Index: 414599 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0840. Min Act: -0.0002

Data Index: 576019 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0860. Min Act: -0.0002

Data Index: 350325 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0834. Min Act: -0.0001

Data Index: 108210 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0774. Min Act: -0.0001

Data Index: 9 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1586632 (Python Code)

Max Activating Token Index: 156

Text #14

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1361370 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0835. Min Act: -0.0001

Data Index: 1486181 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0836. Min Act: -0.0002

Data Index: 119444 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0807. Min Act: -0.0002

Data Index: 448015 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0865. Min Act: -0.0002

Data Index: 1242611 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0858. Min Act: -0.0001

Data Index: 1154487 (C4 (Web Text))

Max Activating Token Index: 880