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

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

Neuron 720 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.9119. Min Act: -0.0000

Data Index: 756622 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.6349. Min Act: -0.0001

Data Index: 1191931 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.3075. Min Act: -0.0001

Data Index: 11561 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.2125. Min Act: -0.0001

Data Index: 565269 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.4474. Min Act: -0.0001

Data Index: 1171009 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.4609. Min Act: -0.0000

Data Index: 34730 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.3102. Min Act: -0.0001

Data Index: 691354 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.3138. Min Act: -0.0000

Data Index: 529752 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.2230. Min Act: -0.0001

Data Index: 185941 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.4771. Min Act: -0.0001

Data Index: 437137 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.1866. Min Act: -0.0001

Data Index: 223677 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.4478. Min Act: -0.0001

Data Index: 1273531 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.2676. Min Act: -0.0001

Data Index: 1119307 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.2999. Min Act: -0.0001

Data Index: 321985 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.4413. Min Act: -0.0001

Data Index: 838098 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.2908. Min Act: -0.0001

Data Index: 165299 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 3.9119. Min Range: -3.9119

Max Act: 2.9069. Min Act: -0.0001

Data Index: 1050794 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.1365. Min Act: -0.0000

Data Index: 957767 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 3.9119. Min Range: -3.9119

Max Act: 3.0210. Min Act: -0.0001

Data Index: 212928 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 3.9119. Min Range: -3.9119

Max Act: 2.8877. Min Act: -0.0001

Data Index: 452079 (C4 (Web Text))

Max Activating Token Index: 848