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

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

Neuron 2033 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: 0.2507. Min Range: -0.2507

Max Act: 0.2464. Min Act: -0.0000

Data Index: 188576 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2507. Min Act: -0.0000

Data Index: 182185 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2447. Min Act: -0.0000

Data Index: 965899 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2050. Min Act: -0.0000

Data Index: 269010 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2187. Min Act: -0.0000

Data Index: 685075 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2252. Min Act: -0.0000

Data Index: 837932 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1371417 (Python Code)

Max Activating Token Index: 748

Text #7

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1323408 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1767. Min Act: -0.0000

Data Index: 858751 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1232067 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1815. Min Act: -0.0000

Data Index: 328739 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1676. Min Act: -0.0000

Data Index: 655646 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1002060 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1308240 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1728. Min Act: -0.0000

Data Index: 1058936 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1657. Min Act: -0.0000

Data Index: 260054 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1636. Min Act: -0.0000

Data Index: 988167 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1549. Min Act: -0.0000

Data Index: 638591 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1000931 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1619. Min Act: -0.0000

Data Index: 1547151 (Python Code)

Max Activating Token Index: 813