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

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

Neuron 2701 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.6349. Min Range: -8.6349

Max Act: 8.6349. Min Act: -0.0001

Data Index: 650627 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 8.6349. Min Range: -8.6349

Max Act: 7.6226. Min Act: -0.0001

Data Index: 446213 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 8.6349. Min Range: -8.6349

Max Act: 7.4293. Min Act: -0.0001

Data Index: 1213327 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 8.6349. Min Range: -8.6349

Max Act: 6.8452. Min Act: -0.0001

Data Index: 531488 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 8.6349. Min Range: -8.6349

Max Act: 7.3142. Min Act: -0.0001

Data Index: 917577 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 8.6349. Min Range: -8.6349

Max Act: 7.2523. Min Act: -0.0001

Data Index: 842270 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 8.6349. Min Range: -8.6349

Max Act: 7.1336. Min Act: -0.0001

Data Index: 1317633 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 8.6349. Min Range: -8.6349

Max Act: 7.3812. Min Act: -0.0001

Data Index: 1047801 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 8.6349. Min Range: -8.6349

Max Act: 6.6994. Min Act: -0.0001

Data Index: 15378 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 8.6349. Min Range: -8.6349

Max Act: 6.8291. Min Act: -0.0001

Data Index: 108107 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 8.6349. Min Range: -8.6349

Max Act: 6.4826. Min Act: -0.0001

Data Index: 1230812 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 8.6349. Min Range: -8.6349

Max Act: 6.9433. Min Act: -0.0001

Data Index: 1183813 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 8.6349. Min Range: -8.6349

Max Act: 7.0475. Min Act: -0.0001

Data Index: 922867 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 8.6349. Min Range: -8.6349

Max Act: 6.4232. Min Act: -0.0001

Data Index: 137831 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 8.6349. Min Range: -8.6349

Max Act: 7.0570. Min Act: -0.0001

Data Index: 585599 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 8.6349. Min Range: -8.6349

Max Act: 6.1254. Min Act: -0.0001

Data Index: 7020 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 8.6349. Min Range: -8.6349

Max Act: 6.5683. Min Act: -0.0001

Data Index: 72799 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 8.6349. Min Range: -8.6349

Max Act: 6.0331. Min Act: -0.0001

Data Index: 889318 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 8.6349. Min Range: -8.6349

Max Act: 6.3494. Min Act: -0.0001

Data Index: 586867 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 8.6349. Min Range: -8.6349

Max Act: 6.1642. Min Act: -0.0001

Data Index: 854755 (C4 (Web Text))

Max Activating Token Index: 414