Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 206 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0398. Min Range: -1.0398

Max Act: 1.0177. Min Act: -0.0001

Data Index: 631305 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.9253. Min Act: -0.0001

Data Index: 156830 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.9936. Min Act: -0.0001

Data Index: 1150258 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 1.0398. Min Range: -1.0398

Max Act: 1.0389. Min Act: -0.0001

Data Index: 1139854 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.8644. Min Act: -0.0001

Data Index: 267506 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 1.0398. Min Range: -1.0398

Max Act: 1.0398. Min Act: -0.0001

Data Index: 1350223 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.8791. Min Act: -0.0001

Data Index: 400785 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.8724. Min Act: -0.0001

Data Index: 717467 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.8290. Min Act: -0.0001

Data Index: 830367 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.9346. Min Act: -0.0001

Data Index: 124653 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.8814. Min Act: -0.0001

Data Index: 71428 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7709. Min Act: -0.0001

Data Index: 1131356 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.8345. Min Act: -0.0001

Data Index: 1029307 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.8026. Min Act: -0.0001

Data Index: 363888 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.6960. Min Act: -0.0001

Data Index: 1351847 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.8660. Min Act: -0.0001

Data Index: 382614 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7566. Min Act: -0.0001

Data Index: 247778 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7761. Min Act: -0.0001

Data Index: 71504 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.6679. Min Act: -0.0001

Data Index: 466369 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.8802. Min Act: -0.0001

Data Index: 1603354 (Python Code)

Max Activating Token Index: 621