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

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

Neuron 1686 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: 0.3905. Min Range: -0.3905

Max Act: 0.3905. Min Act: -0.0000

Data Index: 457832 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1008788 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3423. Min Act: -0.0000

Data Index: 306730 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2964. Min Act: -0.0000

Data Index: 820316 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1124921 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1077800 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3165. Min Act: -0.0000

Data Index: 608826 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1087081 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1194209 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1160792 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1127471 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2562. Min Act: -0.0000

Data Index: 312699 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2726. Min Act: -0.0000

Data Index: 85545 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1187003 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2508. Min Act: -0.0000

Data Index: 452481 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2353. Min Act: -0.0000

Data Index: 988631 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2479. Min Act: -0.0000

Data Index: 988221 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2439. Min Act: -0.0000

Data Index: 315264 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2459. Min Act: -0.0000

Data Index: 261576 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1185084 (C4 (Web Text))

Max Activating Token Index: 761