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

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

Neuron 1909 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1967. Min Act: -0.0000

Data Index: 445392 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1798. Min Act: -0.0000

Data Index: 477600 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1419. Min Act: -0.0000

Data Index: 167593 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1263. Min Act: -0.0000

Data Index: 627119 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1075. Min Act: -0.0000

Data Index: 299068 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1120. Min Act: -0.0000

Data Index: 834827 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1106. Min Act: -0.0000

Data Index: 299779 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1010. Min Act: -0.0000

Data Index: 564593 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1077. Min Act: -0.0000

Data Index: 948330 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1090. Min Act: -0.0000

Data Index: 478328 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1247629 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1149619 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.0836. Min Act: -0.0000

Data Index: 885548 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.0980. Min Act: -0.0000

Data Index: 205506 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.0911. Min Act: -0.0000

Data Index: 51061 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.0922. Min Act: -0.0000

Data Index: 797184 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.0856. Min Act: -0.0000

Data Index: 883068 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1238975 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.0924. Min Act: -0.0000

Data Index: 471045 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1043675 (C4 (Web Text))

Max Activating Token Index: 19