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

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

Neuron 3824 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: 1.2132. Min Range: -1.2132

Max Act: 1.2132. Min Act: -0.0000

Data Index: 1458752 (Python Code)

Max Activating Token Index: 714

Text #1

Max Range: 1.2132. Min Range: -1.2132

Max Act: 1.1895. Min Act: -0.0000

Data Index: 1543040 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 1.2132. Min Range: -1.2132

Max Act: 1.1224. Min Act: -0.0000

Data Index: 1490796 (Python Code)

Max Activating Token Index: 469

Text #3

Max Range: 1.2132. Min Range: -1.2132

Max Act: 1.0567. Min Act: -0.0000

Data Index: 390444 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 1.2132. Min Range: -1.2132

Max Act: 1.0382. Min Act: -0.0000

Data Index: 943868 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 1.2132. Min Range: -1.2132

Max Act: 1.0573. Min Act: -0.0000

Data Index: 1593310 (Python Code)

Max Activating Token Index: 468

Text #6

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.9817. Min Act: -0.0001

Data Index: 1605353 (Python Code)

Max Activating Token Index: 411

Text #7

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.9754. Min Act: -0.0001

Data Index: 376774 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.9360. Min Act: -0.0001

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.8764. Min Act: -0.0001

Data Index: 1551816 (Python Code)

Max Activating Token Index: 248

Text #10

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.9222. Min Act: -0.0001

Data Index: 843315 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.8056. Min Act: -0.0001

Data Index: 387387 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.8136. Min Act: -0.0000

Data Index: 757353 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1525405 (Python Code)

Max Activating Token Index: 430

Text #14

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.8002. Min Act: -0.0001

Data Index: 1595939 (Python Code)

Max Activating Token Index: 639

Text #15

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.8455. Min Act: -0.0000

Data Index: 1375673 (Python Code)

Max Activating Token Index: 160

Text #16

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.7886. Min Act: -0.0001

Data Index: 388108 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.8195. Min Act: -0.0001

Data Index: 1466615 (Python Code)

Max Activating Token Index: 198

Text #18

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.7910. Min Act: -0.0001

Data Index: 940402 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 1.2132. Min Range: -1.2132

Max Act: 0.7837. Min Act: -0.0001

Data Index: 1419552 (Python Code)

Max Activating Token Index: 492