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

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

Neuron 2039 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7285. Min Act: -0.0002

Data Index: 846828 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7703. Min Act: -0.0002

Data Index: 780564 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.8156. Min Act: -0.0002

Data Index: 415356 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.8747. Min Act: -0.0002

Data Index: 248463 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7085. Min Act: -0.0002

Data Index: 1339747 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7653. Min Act: -0.0002

Data Index: 596057 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7564. Min Act: -0.0002

Data Index: 1003308 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7549. Min Act: -0.0002

Data Index: 829616 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7050. Min Act: -0.0002

Data Index: 784955 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7402. Min Act: -0.0002

Data Index: 1053395 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7708. Min Act: -0.0002

Data Index: 1225470 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7130. Min Act: -0.0002

Data Index: 936396 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7052. Min Act: -0.0002

Data Index: 674573 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6697. Min Act: -0.0002

Data Index: 287285 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6523. Min Act: -0.0002

Data Index: 179425 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6088. Min Act: -0.0002

Data Index: 661609 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7292. Min Act: -0.0002

Data Index: 1143504 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7355. Min Act: -0.0002

Data Index: 1187780 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.7335. Min Act: -0.0002

Data Index: 1185508 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.8747. Min Range: -0.8747

Max Act: 0.6930. Min Act: -0.0002

Data Index: 959598 (C4 (Web Text))

Max Activating Token Index: 698