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

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

Neuron 872 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.1964. Min Act: -0.0002

Data Index: 151992 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.2067. Min Act: -0.0002

Data Index: 252712 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.0889. Min Act: -0.0002

Data Index: 522173 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.1984. Min Act: -0.0002

Data Index: 772829 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.2144. Min Act: -0.0002

Data Index: 1334244 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.1397. Min Act: -0.0002

Data Index: 903600 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.1423. Min Act: -0.0002

Data Index: 1024988 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.0761. Min Act: -0.0002

Data Index: 468980 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.1535. Min Act: -0.0002

Data Index: 430932 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.0559. Min Act: -0.0002

Data Index: 253666 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.1229. Min Act: -0.0002

Data Index: 483345 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.1666. Min Act: -0.0002

Data Index: 402446 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.0857. Min Act: -0.0002

Data Index: 1215828 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.1052. Min Act: -0.0001

Data Index: 54334 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.0723. Min Act: -0.0001

Data Index: 409062 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.0660. Min Act: -0.0002

Data Index: 123540 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.0421. Min Act: -0.0002

Data Index: 351748 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.0305. Min Act: -0.0002

Data Index: 123173 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.0967. Min Act: -0.0001

Data Index: 397831 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 1.2144. Min Range: -1.2144

Max Act: 1.0590. Min Act: -0.0002

Data Index: 34554 (C4 (Web Text))

Max Activating Token Index: 460