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

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

Neuron 4127 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2796. Min Range: -2.2796

Max Act: 2.2796. Min Act: -0.0000

Data Index: 1285736 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 2.2796. Min Range: -2.2796

Max Act: 2.0849. Min Act: -0.0000

Data Index: 1017998 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.9961. Min Act: -0.0000

Data Index: 440988 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.9197. Min Act: -0.0000

Data Index: 1461872 (Python Code)

Max Activating Token Index: 403

Text #4

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.8657. Min Act: -0.0000

Data Index: 1530626 (Python Code)

Max Activating Token Index: 146

Text #5

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.9607. Min Act: -0.0000

Data Index: 1007643 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.9961. Min Act: -0.0000

Data Index: 1285854 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.7328. Min Act: -0.0000

Data Index: 1533644 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.5861. Min Act: -0.0000

Data Index: 1077252 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.5913. Min Act: -0.0000

Data Index: 1084450 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.5639. Min Act: -0.0000

Data Index: 63867 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.4996. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.5065. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.5116. Min Act: -0.0000

Data Index: 107102 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.4974. Min Act: -0.0000

Data Index: 194775 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.3839. Min Act: -0.0000

Data Index: 726745 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.3784. Min Act: -0.0000

Data Index: 158197 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.3710. Min Act: -0.0000

Data Index: 1130262 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.3586. Min Act: -0.0000

Data Index: 1453129 (Python Code)

Max Activating Token Index: 630

Text #19

Max Range: 2.2796. Min Range: -2.2796

Max Act: 1.2775. Min Act: -0.0000

Data Index: 1213113 (C4 (Web Text))

Max Activating Token Index: 828