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

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

Neuron 637 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: 0.4258. Min Range: -0.4258

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1400426 (Python Code)

Max Activating Token Index: 139

Text #1

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.3337. Min Act: -0.0000

Data Index: 170020 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.3202. Min Act: -0.0000

Data Index: 172886 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1408063 (Python Code)

Max Activating Token Index: 574

Text #4

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1609866 (Python Code)

Max Activating Token Index: 57

Text #5

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1039618 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2699. Min Act: -0.0000

Data Index: 998554 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2671. Min Act: -0.0000

Data Index: 693941 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2647. Min Act: -0.0000

Data Index: 488105 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2552. Min Act: -0.0000

Data Index: 543799 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1643024 (Python Code)

Max Activating Token Index: 382

Text #11

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1136233 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1531093 (Python Code)

Max Activating Token Index: 313

Text #13

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1346935 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2384. Min Act: -0.0000

Data Index: 228694 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2850. Min Act: -0.0000

Data Index: 55493 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1179938 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1049800 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1158510 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.4258. Min Range: -0.4258

Max Act: 0.2167. Min Act: -0.0000

Data Index: 1079717 (C4 (Web Text))

Max Activating Token Index: 201