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

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

Neuron 467 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: 0.8109. Min Range: -0.8109

Max Act: 0.8109. Min Act: -0.0002

Data Index: 549861 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.6673. Min Act: -0.0002

Data Index: 217344 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.6546. Min Act: -0.0001

Data Index: 563536 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.6656. Min Act: -0.0001

Data Index: 1053679 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.5315. Min Act: -0.0001

Data Index: 807693 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.5673. Min Act: -0.0002

Data Index: 118668 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.6717. Min Act: -0.0002

Data Index: 1168132 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.6000. Min Act: -0.0002

Data Index: 46647 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.6629. Min Act: -0.0002

Data Index: 437172 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.6160. Min Act: -0.0002

Data Index: 989265 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.5947. Min Act: -0.0002

Data Index: 986134 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.6042. Min Act: -0.0002

Data Index: 125922 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.5986. Min Act: -0.0002

Data Index: 193389 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.6141. Min Act: -0.0002

Data Index: 438114 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.6316. Min Act: -0.0001

Data Index: 960355 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.5695. Min Act: -0.0001

Data Index: 1167303 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.6087. Min Act: -0.0002

Data Index: 408158 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.5334. Min Act: -0.0001

Data Index: 1160664 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.6557. Min Act: -0.0001

Data Index: 770710 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.8109. Min Range: -0.8109

Max Act: 0.5498. Min Act: -0.0002

Data Index: 543218 (C4 (Web Text))

Max Activating Token Index: 330