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

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

Neuron 3911 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.9002. Min Act: -0.0001

Data Index: 62293 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8403. Min Act: -0.0001

Data Index: 411430 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8880. Min Act: -0.0001

Data Index: 1034085 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8489. Min Act: -0.0001

Data Index: 858853 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.9082. Min Act: -0.0001

Data Index: 827817 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8092. Min Act: -0.0001

Data Index: 189401 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8745. Min Act: -0.0001

Data Index: 1057113 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8287. Min Act: -0.0001

Data Index: 357738 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8320. Min Act: -0.0001

Data Index: 290089 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8283. Min Act: -0.0001

Data Index: 301872 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7861. Min Act: -0.0001

Data Index: 1106630 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7934. Min Act: -0.0001

Data Index: 545692 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7852. Min Act: -0.0001

Data Index: 119570 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8116. Min Act: -0.0001

Data Index: 635408 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8559. Min Act: -0.0001

Data Index: 1183311 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8222. Min Act: -0.0001

Data Index: 771474 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8164. Min Act: -0.0001

Data Index: 43952 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7870. Min Act: -0.0001

Data Index: 285521 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8200. Min Act: -0.0001

Data Index: 808733 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7617. Min Act: -0.0001

Data Index: 360003 (C4 (Web Text))

Max Activating Token Index: 312