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

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

Neuron 505 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0382. Min Range: -1.0382

Max Act: 1.0382. Min Act: -0.0001

Data Index: 383636 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8063. Min Act: -0.0001

Data Index: 182088 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8813. Min Act: -0.0001

Data Index: 688398 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7703. Min Act: -0.0000

Data Index: 216545 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7156. Min Act: -0.0000

Data Index: 999730 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7133. Min Act: -0.0000

Data Index: 377246 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7295. Min Act: -0.0001

Data Index: 432727 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7406. Min Act: -0.0000

Data Index: 633551 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1122487 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7051. Min Act: -0.0000

Data Index: 909041 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.6774. Min Act: -0.0001

Data Index: 221504 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7048. Min Act: -0.0000

Data Index: 304111 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1277280 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1315784 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1104161 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.6137. Min Act: -0.0000

Data Index: 643208 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1286487 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.6961. Min Act: -0.0000

Data Index: 420000 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1069041 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.6493. Min Act: -0.0000

Data Index: 856093 (C4 (Web Text))

Max Activating Token Index: 330