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

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

Neuron 4438 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8241. Min Range: -5.8241

Max Act: 5.8241. Min Act: -0.0000

Data Index: 1046071 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 5.8241. Min Range: -5.8241

Max Act: 5.1440. Min Act: -0.0000

Data Index: 517381 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 5.8241. Min Range: -5.8241

Max Act: 5.0523. Min Act: -0.0000

Data Index: 1103833 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 5.8241. Min Range: -5.8241

Max Act: 5.2023. Min Act: -0.0001

Data Index: 742789 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 5.8241. Min Range: -5.8241

Max Act: 4.7247. Min Act: -0.0000

Data Index: 423188 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 5.8241. Min Range: -5.8241

Max Act: 4.8010. Min Act: -0.0000

Data Index: 331124 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 5.8241. Min Range: -5.8241

Max Act: 5.0857. Min Act: -0.0000

Data Index: 565331 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 5.8241. Min Range: -5.8241

Max Act: 4.0338. Min Act: -0.0000

Data Index: 312575 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 5.8241. Min Range: -5.8241

Max Act: 3.8660. Min Act: -0.0000

Data Index: 503180 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 5.8241. Min Range: -5.8241

Max Act: 3.4906. Min Act: -0.0001

Data Index: 1276570 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 5.8241. Min Range: -5.8241

Max Act: 3.7511. Min Act: -0.0000

Data Index: 166461 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 5.8241. Min Range: -5.8241

Max Act: 4.0216. Min Act: -0.0001

Data Index: 1095147 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 5.8241. Min Range: -5.8241

Max Act: 4.0238. Min Act: -0.0000

Data Index: 926910 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 5.8241. Min Range: -5.8241

Max Act: 3.7731. Min Act: -0.0000

Data Index: 200798 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 5.8241. Min Range: -5.8241

Max Act: 3.8732. Min Act: -0.0000

Data Index: 828000 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 5.8241. Min Range: -5.8241

Max Act: 3.6693. Min Act: -0.0000

Data Index: 995248 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 5.8241. Min Range: -5.8241

Max Act: 3.9799. Min Act: -0.0000

Data Index: 185129 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 5.8241. Min Range: -5.8241

Max Act: 3.7242. Min Act: -0.0001

Data Index: 1291402 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 5.8241. Min Range: -5.8241

Max Act: 3.3049. Min Act: -0.0000

Data Index: 369647 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 5.8241. Min Range: -5.8241

Max Act: 3.4724. Min Act: -0.0000

Data Index: 1352705 (C4 (Web Text))

Max Activating Token Index: 6