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

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

Neuron 1991 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8908. Min Act: -0.0000

Data Index: 983477 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8654. Min Act: -0.0000

Data Index: 533770 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8442. Min Act: -0.0000

Data Index: 576199 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1008661 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8617. Min Act: -0.0000

Data Index: 759796 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1087078 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8625. Min Act: -0.0000

Data Index: 904294 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8314. Min Act: -0.0000

Data Index: 946930 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1237020 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7471. Min Act: -0.0000

Data Index: 801417 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1120377 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8088. Min Act: -0.0000

Data Index: 87599 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8056. Min Act: -0.0000

Data Index: 968648 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8009. Min Act: -0.0000

Data Index: 765474 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7479. Min Act: -0.0000

Data Index: 11799 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1059609 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7433. Min Act: -0.0000

Data Index: 849692 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1061657 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7837. Min Act: -0.0000

Data Index: 324779 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1200457 (C4 (Web Text))

Max Activating Token Index: 538