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

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

Neuron 5108 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3040. Min Range: -1.3040

Max Act: 1.3040. Min Act: -0.0000

Data Index: 364445 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 1.3040. Min Range: -1.3040

Max Act: 1.0681. Min Act: -0.0000

Data Index: 339102 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 1.3040. Min Range: -1.3040

Max Act: 1.0562. Min Act: -0.0000

Data Index: 413979 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1227531 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.9488. Min Act: -0.0000

Data Index: 925989 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.9322. Min Act: -0.0000

Data Index: 313235 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.9113. Min Act: -0.0000

Data Index: 218061 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.8496. Min Act: -0.0000

Data Index: 431455 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.8690. Min Act: -0.0000

Data Index: 144278 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.8981. Min Act: -0.0000

Data Index: 918944 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.8351. Min Act: -0.0000

Data Index: 778431 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.8594. Min Act: -0.0000

Data Index: 584656 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.8671. Min Act: -0.0000

Data Index: 499811 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.7361. Min Act: -0.0000

Data Index: 735052 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.8147. Min Act: -0.0000

Data Index: 240179 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.8066. Min Act: -0.0000

Data Index: 32508 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.7740. Min Act: -0.0000

Data Index: 526455 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.7932. Min Act: -0.0000

Data Index: 865485 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.8461. Min Act: -0.0000

Data Index: 694609 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.7864. Min Act: -0.0000

Data Index: 832504 (C4 (Web Text))

Max Activating Token Index: 361