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

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

Neuron 4817 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.3536. Min Act: -0.0000

Data Index: 86821 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2491. Min Act: -0.0000

Data Index: 1214026 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2003. Min Act: -0.0000

Data Index: 28732 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1693. Min Act: -0.0000

Data Index: 541747 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2012. Min Act: -0.0000

Data Index: 162827 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2643. Min Act: -0.0000

Data Index: 1077 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2067. Min Act: -0.0000

Data Index: 1347351 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1547. Min Act: -0.0000

Data Index: 857885 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0950. Min Act: -0.0000

Data Index: 937323 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1888. Min Act: -0.0000

Data Index: 479608 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1214. Min Act: -0.0000

Data Index: 857531 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1352. Min Act: -0.0000

Data Index: 537483 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0968. Min Act: -0.0000

Data Index: 757515 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1147631 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0466. Min Act: -0.0000

Data Index: 513401 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 1.3536. Min Range: -1.3536

Max Act: 0.9275. Min Act: -0.0000

Data Index: 164689 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 1.3536. Min Range: -1.3536

Max Act: 0.9217. Min Act: -0.0000

Data Index: 598169 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0309. Min Act: -0.0000

Data Index: 648385 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.3536. Min Range: -1.3536

Max Act: 0.9676. Min Act: -0.0000

Data Index: 153226 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0032. Min Act: -0.0000

Data Index: 689568 (C4 (Web Text))

Max Activating Token Index: 873