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

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

Neuron 4611 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.5681. Min Act: -0.0000

Data Index: 1020645 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.3879. Min Act: -0.0000

Data Index: 169930 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.2925. Min Act: -0.0000

Data Index: 1089849 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.2771. Min Act: -0.0000

Data Index: 843010 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.2712. Min Act: -0.0000

Data Index: 1187535 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.2269. Min Act: -0.0000

Data Index: 1078709 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.2919. Min Act: -0.0000

Data Index: 999208 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.1214. Min Act: -0.0000

Data Index: 222961 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.1962. Min Act: -0.0000

Data Index: 356980 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.1782. Min Act: -0.0000

Data Index: 1259291 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.1800. Min Act: -0.0000

Data Index: 303344 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.1688. Min Act: -0.0000

Data Index: 1125414 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.0339. Min Act: -0.0000

Data Index: 508248 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.0912. Min Act: -0.0000

Data Index: 370027 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.1043. Min Act: -0.0000

Data Index: 480386 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.0585. Min Act: -0.0000

Data Index: 1016264 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.0690. Min Act: -0.0000

Data Index: 891730 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.1243. Min Act: -0.0000

Data Index: 119623 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.0628. Min Act: -0.0000

Data Index: 1204377 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 1.5681. Min Range: -1.5681

Max Act: 0.9886. Min Act: -0.0000

Data Index: 615773 (C4 (Web Text))

Max Activating Token Index: 968