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

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

Neuron 1034 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.5957. Min Act: -0.0000

Data Index: 429640 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.5100. Min Act: -0.0000

Data Index: 192137 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1321477 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4226. Min Act: -0.0000

Data Index: 409479 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.4039. Min Act: -0.0000

Data Index: 1006867 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1155852 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3953. Min Act: -0.0000

Data Index: 754296 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3958. Min Act: -0.0000

Data Index: 831350 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3736. Min Act: -0.0000

Data Index: 489859 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1066178 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3822. Min Act: -0.0000

Data Index: 823219 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3673. Min Act: -0.0000

Data Index: 273704 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3891. Min Act: -0.0000

Data Index: 706949 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3640. Min Act: -0.0000

Data Index: 517676 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3687. Min Act: -0.0000

Data Index: 779526 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3690. Min Act: -0.0000

Data Index: 493598 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3601. Min Act: -0.0000

Data Index: 185899 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3745. Min Act: -0.0000

Data Index: 284088 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1204496 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.5957. Min Range: -0.5957

Max Act: 0.3526. Min Act: -0.0000

Data Index: 157052 (C4 (Web Text))

Max Activating Token Index: 309