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

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

Neuron 3631 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.3147. Min Act: -0.0000

Data Index: 668143 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0291. Min Act: -0.0000

Data Index: 818762 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.2090. Min Act: -0.0000

Data Index: 433058 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1207. Min Act: -0.0000

Data Index: 69205 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1411. Min Act: -0.0000

Data Index: 762322 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0802. Min Act: -0.0000

Data Index: 748083 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1349. Min Act: -0.0000

Data Index: 766949 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0375. Min Act: -0.0000

Data Index: 501074 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.9904. Min Act: -0.0000

Data Index: 72028 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0269. Min Act: -0.0000

Data Index: 626100 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1106050 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0600. Min Act: -0.0000

Data Index: 159102 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0822. Min Act: -0.0000

Data Index: 242695 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0450. Min Act: -0.0000

Data Index: 1209442 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.9605. Min Act: -0.0000

Data Index: 978297 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1102767 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.9738. Min Act: -0.0000

Data Index: 63372 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.9393. Min Act: -0.0000

Data Index: 839648 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.9391. Min Act: -0.0000

Data Index: 403756 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.9186. Min Act: -0.0000

Data Index: 1337398 (C4 (Web Text))

Max Activating Token Index: 744