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

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

Neuron 5560 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: 1.7452. Min Range: -1.7452

Max Act: 1.7452. Min Act: -0.0000

Data Index: 1192574 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 1.7452. Min Range: -1.7452

Max Act: 1.3058. Min Act: -0.0000

Data Index: 1043603 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 1.7452. Min Range: -1.7452

Max Act: 1.2248. Min Act: -0.0000

Data Index: 1171767 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 1.7452. Min Range: -1.7452

Max Act: 1.0823. Min Act: -0.0000

Data Index: 1331213 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 1.7452. Min Range: -1.7452

Max Act: 1.1014. Min Act: -0.0000

Data Index: 963998 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 1.7452. Min Range: -1.7452

Max Act: 1.0637. Min Act: -0.0000

Data Index: 882658 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 1.7452. Min Range: -1.7452

Max Act: 1.0927. Min Act: -0.0000

Data Index: 296630 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 1.7452. Min Range: -1.7452

Max Act: 1.0312. Min Act: -0.0000

Data Index: 1167468 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 1.7452. Min Range: -1.7452

Max Act: 1.0181. Min Act: -0.0000

Data Index: 254718 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 1.7452. Min Range: -1.7452

Max Act: 1.0381. Min Act: -0.0001

Data Index: 1335906 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 1.7452. Min Range: -1.7452

Max Act: 1.0282. Min Act: -0.0000

Data Index: 1216575 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 1.7452. Min Range: -1.7452

Max Act: 1.0290. Min Act: -0.0000

Data Index: 190151 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 1.7452. Min Range: -1.7452

Max Act: 0.9895. Min Act: -0.0000

Data Index: 112787 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 1.7452. Min Range: -1.7452

Max Act: 1.0376. Min Act: -0.0000

Data Index: 593698 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 1.7452. Min Range: -1.7452

Max Act: 0.9847. Min Act: -0.0000

Data Index: 232283 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 1.7452. Min Range: -1.7452

Max Act: 0.9729. Min Act: -0.0000

Data Index: 84530 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 1.7452. Min Range: -1.7452

Max Act: 0.9622. Min Act: -0.0000

Data Index: 964572 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 1.7452. Min Range: -1.7452

Max Act: 0.9919. Min Act: -0.0000

Data Index: 130101 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 1.7452. Min Range: -1.7452

Max Act: 0.9243. Min Act: -0.0000

Data Index: 873571 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 1.7452. Min Range: -1.7452

Max Act: 0.9731. Min Act: -0.0000

Data Index: 201796 (C4 (Web Text))

Max Activating Token Index: 597