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

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

Neuron 854 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.8222. Min Act: -0.0000

Data Index: 347176 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.7906. Min Act: -0.0000

Data Index: 1182727 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.6967. Min Act: -0.0000

Data Index: 1463120 (Python Code)

Max Activating Token Index: 839

Text #3

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.6953. Min Act: -0.0001

Data Index: 729158 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.5749. Min Act: -0.0001

Data Index: 44767 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.5692. Min Act: -0.0001

Data Index: 276467 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.7115. Min Act: -0.0001

Data Index: 421096 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.6516. Min Act: -0.0000

Data Index: 112641 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.6186. Min Act: -0.0000

Data Index: 590324 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.5718. Min Act: -0.0001

Data Index: 1170220 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.6476. Min Act: -0.0000

Data Index: 1146508 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.5632. Min Act: -0.0001

Data Index: 395268 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.5807. Min Act: -0.0000

Data Index: 109938 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.5711. Min Act: -0.0000

Data Index: 14736 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.4914. Min Act: -0.0000

Data Index: 312556 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.5708. Min Act: -0.0000

Data Index: 1569029 (Python Code)

Max Activating Token Index: 987

Text #16

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.4531. Min Act: -0.0001

Data Index: 1329310 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.5107. Min Act: -0.0000

Data Index: 1357186 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.5023. Min Act: -0.0000

Data Index: 411740 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 1.8222. Min Range: -1.8222

Max Act: 1.5282. Min Act: -0.0001

Data Index: 568392 (C4 (Web Text))

Max Activating Token Index: 287