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

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

Neuron 2606 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.6292. Min Act: -0.0000

Data Index: 123825 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5422. Min Act: -0.0000

Data Index: 1107109 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5304. Min Act: -0.0001

Data Index: 68881 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5076. Min Act: -0.0001

Data Index: 198733 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5036. Min Act: -0.0001

Data Index: 52831 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4948. Min Act: -0.0000

Data Index: 398208 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5024. Min Act: -0.0001

Data Index: 485870 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.5226. Min Act: -0.0000

Data Index: 139440 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4863. Min Act: -0.0001

Data Index: 676775 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4745. Min Act: -0.0001

Data Index: 899891 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1292238 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4790. Min Act: -0.0000

Data Index: 437223 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4571. Min Act: -0.0000

Data Index: 261904 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4865. Min Act: -0.0000

Data Index: 350529 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4669. Min Act: -0.0000

Data Index: 997197 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4683. Min Act: -0.0001

Data Index: 510626 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1067268 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4457. Min Act: -0.0001

Data Index: 660446 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4552. Min Act: -0.0001

Data Index: 1167225 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.6292. Min Range: -0.6292

Max Act: 0.4372. Min Act: -0.0000

Data Index: 614008 (C4 (Web Text))

Max Activating Token Index: 114