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

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

Neuron 1438 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.6220. Min Act: -0.0000

Data Index: 38179 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.3374. Min Act: -0.0000

Data Index: 588883 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2954. Min Act: -0.0000

Data Index: 890764 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2654. Min Act: -0.0001

Data Index: 119807 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2959. Min Act: -0.0000

Data Index: 782212 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2761. Min Act: -0.0000

Data Index: 540794 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1027557 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1203564 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2598. Min Act: -0.0000

Data Index: 358635 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2752. Min Act: -0.0000

Data Index: 671990 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2545. Min Act: -0.0000

Data Index: 250969 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2700. Min Act: -0.0001

Data Index: 610602 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2076. Min Act: -0.0000

Data Index: 486946 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2385. Min Act: -0.0000

Data Index: 555797 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2369. Min Act: -0.0000

Data Index: 633971 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1144562 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2031. Min Act: -0.0000

Data Index: 893696 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1331840 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2058. Min Act: -0.0000

Data Index: 165460 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.1907. Min Act: -0.0000

Data Index: 36195 (C4 (Web Text))

Max Activating Token Index: 485