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

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

Neuron 1927 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1429706 (Python Code)

Max Activating Token Index: 190

Text #1

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1036636 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0341. Min Act: -0.0003

Data Index: 1168008 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0319. Min Act: -0.0003

Data Index: 387757 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0307. Min Act: -0.0003

Data Index: 425423 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1086716 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1133069 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0306. Min Act: -0.0003

Data Index: 497408 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0280. Min Act: -0.0003

Data Index: 675229 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1322052 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0299. Min Act: -0.0003

Data Index: 676794 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1328190 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1465799 (Python Code)

Max Activating Token Index: 66

Text #13

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0286. Min Act: -0.0003

Data Index: 371176 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1281363 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0271. Min Act: -0.0003

Data Index: 315936 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1506010 (Python Code)

Max Activating Token Index: 779

Text #17

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0283. Min Act: -0.0003

Data Index: 761668 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0275. Min Act: -0.0003

Data Index: 655040 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1479030 (Python Code)

Max Activating Token Index: 919