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

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

Neuron 778 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: 0.2449. Min Range: -0.2449

Max Act: 0.2449. Min Act: -0.0000

Data Index: 703407 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2177. Min Act: -0.0000

Data Index: 196005 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1985. Min Act: -0.0000

Data Index: 192863 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1001645 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1028520 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1821. Min Act: -0.0000

Data Index: 63334 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1808. Min Act: -0.0000

Data Index: 345349 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1847. Min Act: -0.0000

Data Index: 415738 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1653. Min Act: -0.0000

Data Index: 896589 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1690. Min Act: -0.0000

Data Index: 591861 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1585. Min Act: -0.0000

Data Index: 1161165 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1628. Min Act: -0.0000

Data Index: 581223 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1839. Min Act: -0.0000

Data Index: 771325 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1596. Min Act: -0.0000

Data Index: 372847 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1765. Min Act: -0.0000

Data Index: 805912 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1622. Min Act: -0.0000

Data Index: 57256 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1596. Min Act: -0.0000

Data Index: 879656 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1676. Min Act: -0.0000

Data Index: 469156 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1467. Min Act: -0.0000

Data Index: 1021435 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1510. Min Act: -0.0000

Data Index: 495050 (C4 (Web Text))

Max Activating Token Index: 576