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

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

Neuron 2518 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2516. Min Act: -0.0000

Data Index: 316518 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1607. Min Act: -0.0001

Data Index: 552448 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1476. Min Act: -0.0000

Data Index: 859476 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1401. Min Act: -0.0000

Data Index: 649640 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1308. Min Act: -0.0001

Data Index: 147988 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1273. Min Act: -0.0001

Data Index: 356020 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1326. Min Act: -0.0001

Data Index: 223519 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1324. Min Act: -0.0001

Data Index: 163851 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1351. Min Act: -0.0000

Data Index: 894797 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1235. Min Act: -0.0000

Data Index: 607250 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1274. Min Act: -0.0001

Data Index: 611422 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1158. Min Act: -0.0001

Data Index: 505862 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1022. Min Act: -0.0000

Data Index: 692452 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1141. Min Act: -0.0000

Data Index: 886838 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1025. Min Act: -0.0000

Data Index: 459884 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1105. Min Act: -0.0001

Data Index: 842746 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1149. Min Act: -0.0001

Data Index: 957146 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1104. Min Act: -0.0000

Data Index: 508396 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1131. Min Act: -0.0000

Data Index: 677077 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.0957. Min Act: -0.0000

Data Index: 149373 (C4 (Web Text))

Max Activating Token Index: 348