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

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

Neuron 1173 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.2579. Min Act: -0.0000

Data Index: 1098705 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.2717. Min Act: -0.0000

Data Index: 620882 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1673. Min Act: -0.0000

Data Index: 513263 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1735. Min Act: -0.0000

Data Index: 1016910 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1633. Min Act: -0.0000

Data Index: 14515 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0143. Min Act: -0.0000

Data Index: 1050995 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1274. Min Act: -0.0000

Data Index: 1014503 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1333. Min Act: -0.0000

Data Index: 938719 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1296. Min Act: -0.0000

Data Index: 761172 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.9827. Min Act: -0.0000

Data Index: 1353239 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1312595 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0251. Min Act: -0.0000

Data Index: 65113 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.9453. Min Act: -0.0000

Data Index: 15639 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0032. Min Act: -0.0000

Data Index: 893847 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.9999. Min Act: -0.0000

Data Index: 1120128 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1290783 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.8304. Min Act: -0.0000

Data Index: 583364 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1219926 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 1.2717. Min Range: -1.2717

Max Act: 0.9609. Min Act: -0.0000

Data Index: 531995 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0158. Min Act: -0.0000

Data Index: 640892 (C4 (Web Text))

Max Activating Token Index: 307