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

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

Neuron 2030 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1480416 (Python Code)

Max Activating Token Index: 316

Text #1

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1648934 (Python Code)

Max Activating Token Index: 770

Text #2

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1543375 (Python Code)

Max Activating Token Index: 261

Text #3

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1632066 (Python Code)

Max Activating Token Index: 328

Text #4

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1490191 (Python Code)

Max Activating Token Index: 861

Text #5

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1399680 (Python Code)

Max Activating Token Index: 149

Text #6

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1607633 (Python Code)

Max Activating Token Index: 174

Text #7

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1499190 (Python Code)

Max Activating Token Index: 850

Text #8

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1575827 (Python Code)

Max Activating Token Index: 844

Text #9

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1524169 (Python Code)

Max Activating Token Index: 485

Text #10

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1595295 (Python Code)

Max Activating Token Index: 143

Text #11

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1447352 (Python Code)

Max Activating Token Index: 970

Text #12

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1557226 (Python Code)

Max Activating Token Index: 945

Text #13

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1394342 (Python Code)

Max Activating Token Index: 514

Text #14

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1466658 (Python Code)

Max Activating Token Index: 403

Text #15

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1419772 (Python Code)

Max Activating Token Index: 871

Text #16

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1646531 (Python Code)

Max Activating Token Index: 685

Text #17

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1484184 (Python Code)

Max Activating Token Index: 183

Text #18

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1418880 (Python Code)

Max Activating Token Index: 632

Text #19

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1641104 (Python Code)

Max Activating Token Index: 857