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

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

Neuron 4107 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3682. Min Range: -7.3682

Max Act: 7.3682. Min Act: -0.0000

Data Index: 561470 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 7.3682. Min Range: -7.3682

Max Act: 7.0483. Min Act: -0.0000

Data Index: 253405 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 7.3682. Min Range: -7.3682

Max Act: 6.6927. Min Act: -0.0000

Data Index: 158677 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 7.3682. Min Range: -7.3682

Max Act: 7.0599. Min Act: -0.0000

Data Index: 1007971 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 7.3682. Min Range: -7.3682

Max Act: 7.0813. Min Act: -0.0000

Data Index: 1006024 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 7.3682. Min Range: -7.3682

Max Act: 7.0626. Min Act: -0.0000

Data Index: 97854 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 7.3682. Min Range: -7.3682

Max Act: 6.7302. Min Act: -0.0000

Data Index: 75844 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 7.3682. Min Range: -7.3682

Max Act: 6.5341. Min Act: -0.0000

Data Index: 591510 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 7.3682. Min Range: -7.3682

Max Act: 6.0801. Min Act: -0.0000

Data Index: 478582 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 7.3682. Min Range: -7.3682

Max Act: 6.3015. Min Act: -0.0000

Data Index: 737263 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 7.3682. Min Range: -7.3682

Max Act: 6.1842. Min Act: -0.0000

Data Index: 1054368 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 7.3682. Min Range: -7.3682

Max Act: 5.7348. Min Act: -0.0000

Data Index: 524552 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 7.3682. Min Range: -7.3682

Max Act: 5.5341. Min Act: -0.0000

Data Index: 424398 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 7.3682. Min Range: -7.3682

Max Act: 5.4645. Min Act: -0.0000

Data Index: 1098073 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 7.3682. Min Range: -7.3682

Max Act: 5.4840. Min Act: -0.0000

Data Index: 1093036 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 7.3682. Min Range: -7.3682

Max Act: 5.9696. Min Act: -0.0000

Data Index: 1086434 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 7.3682. Min Range: -7.3682

Max Act: 5.5920. Min Act: -0.0000

Data Index: 215974 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 7.3682. Min Range: -7.3682

Max Act: 4.5989. Min Act: -0.0000

Data Index: 376097 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 7.3682. Min Range: -7.3682

Max Act: 4.9402. Min Act: -0.0000

Data Index: 906189 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 7.3682. Min Range: -7.3682

Max Act: 5.0841. Min Act: -0.0000

Data Index: 1276251 (C4 (Web Text))

Max Activating Token Index: 503