Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1103 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2427. Min Act: -0.0000

Data Index: 965490 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2381. Min Act: -0.0000

Data Index: 495722 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2485. Min Act: -0.0000

Data Index: 1102356 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2242. Min Act: -0.0000

Data Index: 890401 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2106. Min Act: -0.0000

Data Index: 584005 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1166701 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2133. Min Act: -0.0000

Data Index: 520936 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2253. Min Act: -0.0000

Data Index: 761469 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1234288 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2031. Min Act: -0.0000

Data Index: 22715 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2104. Min Act: -0.0000

Data Index: 671955 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2009. Min Act: -0.0000

Data Index: 186873 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1135556 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2075. Min Act: -0.0000

Data Index: 200105 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2112. Min Act: -0.0000

Data Index: 973168 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2038. Min Act: -0.0000

Data Index: 65171 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2104. Min Act: -0.0000

Data Index: 198018 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2039. Min Act: -0.0000

Data Index: 428023 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.2022. Min Act: -0.0000

Data Index: 865652 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.2485. Min Range: -0.2485

Max Act: 0.1881. Min Act: -0.0000

Data Index: 355172 (C4 (Web Text))

Max Activating Token Index: 708