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

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

Neuron 2614 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3885. Min Range: -2.3885

Max Act: 2.3885. Min Act: -0.0000

Data Index: 1508233 (Python Code)

Max Activating Token Index: 1019

Text #1

Max Range: 2.3885. Min Range: -2.3885

Max Act: 2.2625. Min Act: -0.0000

Data Index: 288804 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 2.3885. Min Range: -2.3885

Max Act: 2.0624. Min Act: -0.0000

Data Index: 635613 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 2.3885. Min Range: -2.3885

Max Act: 2.1475. Min Act: -0.0000

Data Index: 1315407 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 2.3885. Min Range: -2.3885

Max Act: 2.1157. Min Act: -0.0000

Data Index: 907421 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 2.3885. Min Range: -2.3885

Max Act: 1.9911. Min Act: -0.0000

Data Index: 928422 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 2.3885. Min Range: -2.3885

Max Act: 2.0612. Min Act: -0.0000

Data Index: 455292 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 2.3885. Min Range: -2.3885

Max Act: 2.1642. Min Act: -0.0000

Data Index: 503240 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 2.3885. Min Range: -2.3885

Max Act: 2.0323. Min Act: -0.0000

Data Index: 467488 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 2.3885. Min Range: -2.3885

Max Act: 1.9069. Min Act: -0.0000

Data Index: 1289823 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 2.3885. Min Range: -2.3885

Max Act: 1.9809. Min Act: -0.0000

Data Index: 1459026 (Python Code)

Max Activating Token Index: 588

Text #11

Max Range: 2.3885. Min Range: -2.3885

Max Act: 1.9833. Min Act: -0.0000

Data Index: 1319925 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 2.3885. Min Range: -2.3885

Max Act: 1.8947. Min Act: -0.0000

Data Index: 234522 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 2.3885. Min Range: -2.3885

Max Act: 1.9275. Min Act: -0.0000

Data Index: 38849 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 2.3885. Min Range: -2.3885

Max Act: 1.9770. Min Act: -0.0000

Data Index: 234428 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 2.3885. Min Range: -2.3885

Max Act: 1.7926. Min Act: -0.0000

Data Index: 385172 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 2.3885. Min Range: -2.3885

Max Act: 2.0996. Min Act: -0.0000

Data Index: 1247820 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 2.3885. Min Range: -2.3885

Max Act: 1.9832. Min Act: -0.0000

Data Index: 818147 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 2.3885. Min Range: -2.3885

Max Act: 2.0110. Min Act: -0.0000

Data Index: 229491 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 2.3885. Min Range: -2.3885

Max Act: 1.7882. Min Act: -0.0000

Data Index: 285025 (C4 (Web Text))

Max Activating Token Index: 67