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

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

Neuron 2017 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0550. Min Act: -0.0003

Data Index: 256705 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0512. Min Act: -0.0003

Data Index: 981148 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1096049 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1215938 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0504. Min Act: -0.0003

Data Index: 1348162 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1150867 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0495. Min Act: -0.0003

Data Index: 366032 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0519. Min Act: -0.0004

Data Index: 250404 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0489. Min Act: -0.0003

Data Index: 776812 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0489. Min Act: -0.0003

Data Index: 392058 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0457. Min Act: -0.0003

Data Index: 914329 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0510. Min Act: -0.0003

Data Index: 508477 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1241259 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0283. Min Act: -0.0003

Data Index: 396849 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0326. Min Act: -0.0003

Data Index: 554549 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0306. Min Act: -0.0003

Data Index: 713820 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1124344 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1646384 (Python Code)

Max Activating Token Index: 517

Text #18

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0294. Min Act: -0.0003

Data Index: 225762 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0280. Min Act: -0.0003

Data Index: 950030 (C4 (Web Text))

Max Activating Token Index: 528