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

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

Neuron 20 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.5193. Min Act: -0.0000

Data Index: 525064 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.2988. Min Act: -0.0000

Data Index: 1204077 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.2599. Min Act: -0.0000

Data Index: 1011327 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.2312. Min Act: -0.0000

Data Index: 1122752 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.0481. Min Act: -0.0000

Data Index: 928996 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.1559. Min Act: -0.0000

Data Index: 971957 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.0113. Min Act: -0.0000

Data Index: 264665 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.8991. Min Act: -0.0000

Data Index: 390018 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.8942. Min Act: -0.0000

Data Index: 191030 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.0372. Min Act: -0.0000

Data Index: 649712 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.9086. Min Act: -0.0000

Data Index: 532092 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.8661. Min Act: -0.0000

Data Index: 529941 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.7334. Min Act: -0.0000

Data Index: 72075 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.0171. Min Act: -0.0000

Data Index: 1031358 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.0776. Min Act: -0.0000

Data Index: 868039 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.1134. Min Act: -0.0000

Data Index: 1315443 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.8101. Min Act: -0.0000

Data Index: 1220464 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.9251. Min Act: -0.0000

Data Index: 349681 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.9298. Min Act: -0.0000

Data Index: 605105 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 3.5193. Min Range: -3.5193

Max Act: 2.8725. Min Act: -0.0000

Data Index: 500801 (C4 (Web Text))

Max Activating Token Index: 874