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

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

Neuron 3864 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7497. Min Range: -2.7497

Max Act: 2.7497. Min Act: -0.0000

Data Index: 894775 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 2.7497. Min Range: -2.7497

Max Act: 2.6465. Min Act: -0.0000

Data Index: 907287 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 2.7497. Min Range: -2.7497

Max Act: 2.5038. Min Act: -0.0000

Data Index: 342264 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 2.7497. Min Range: -2.7497

Max Act: 2.4413. Min Act: -0.0000

Data Index: 758990 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 2.7497. Min Range: -2.7497

Max Act: 2.4125. Min Act: -0.0000

Data Index: 783426 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 2.7497. Min Range: -2.7497

Max Act: 2.1414. Min Act: -0.0000

Data Index: 1097298 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 2.7497. Min Range: -2.7497

Max Act: 2.1473. Min Act: 0.0000

Data Index: 1308372 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 2.7497. Min Range: -2.7497

Max Act: 2.0621. Min Act: -0.0000

Data Index: 1036742 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 2.7497. Min Range: -2.7497

Max Act: 2.0447. Min Act: -0.0000

Data Index: 547183 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 2.7497. Min Range: -2.7497

Max Act: 2.0027. Min Act: -0.0000

Data Index: 1015227 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 2.7497. Min Range: -2.7497

Max Act: 2.0033. Min Act: -0.0000

Data Index: 939603 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 2.7497. Min Range: -2.7497

Max Act: 1.9740. Min Act: -0.0000

Data Index: 281364 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 2.7497. Min Range: -2.7497

Max Act: 1.8014. Min Act: -0.0000

Data Index: 1356742 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 2.7497. Min Range: -2.7497

Max Act: 1.8482. Min Act: -0.0000

Data Index: 1247989 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 2.7497. Min Range: -2.7497

Max Act: 1.7716. Min Act: -0.0000

Data Index: 455614 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 2.7497. Min Range: -2.7497

Max Act: 1.7500. Min Act: -0.0000

Data Index: 755252 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 2.7497. Min Range: -2.7497

Max Act: 1.6635. Min Act: -0.0000

Data Index: 590873 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 2.7497. Min Range: -2.7497

Max Act: 1.7385. Min Act: -0.0000

Data Index: 346268 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 2.7497. Min Range: -2.7497

Max Act: 1.6520. Min Act: -0.0000

Data Index: 624750 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 2.7497. Min Range: -2.7497

Max Act: 1.6356. Min Act: 0.0001

Data Index: 813767 (C4 (Web Text))

Max Activating Token Index: 380