Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2838 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.8214. Min Act: -0.0001

Data Index: 506649 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5948. Min Act: -0.0001

Data Index: 652308 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5944. Min Act: -0.0001

Data Index: 942095 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5903. Min Act: -0.0001

Data Index: 6847 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5862. Min Act: -0.0001

Data Index: 778294 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5590. Min Act: -0.0001

Data Index: 752247 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5639. Min Act: -0.0001

Data Index: 1347449 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5274. Min Act: -0.0001

Data Index: 1283108 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6001. Min Act: -0.0001

Data Index: 1213380 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5315. Min Act: -0.0001

Data Index: 283497 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5186. Min Act: -0.0001

Data Index: 233452 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5380. Min Act: -0.0001

Data Index: 1159567 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5399. Min Act: -0.0001

Data Index: 830499 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5494. Min Act: -0.0001

Data Index: 395405 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5269. Min Act: -0.0001

Data Index: 1046379 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5900. Min Act: -0.0001

Data Index: 847819 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5390. Min Act: -0.0001

Data Index: 518669 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5049. Min Act: -0.0001

Data Index: 257453 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5206. Min Act: -0.0001

Data Index: 1593560 (Python Code)

Max Activating Token Index: 460

Text #19

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5313. Min Act: -0.0001

Data Index: 892751 (C4 (Web Text))

Max Activating Token Index: 779