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

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

Neuron 2803 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.6774. Min Act: -0.0000

Data Index: 1101062 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.5379. Min Act: -0.0000

Data Index: 847079 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.5429. Min Act: -0.0000

Data Index: 13982 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.5259. Min Act: -0.0000

Data Index: 1320585 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.5009. Min Act: -0.0000

Data Index: 924102 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.5785. Min Act: -0.0000

Data Index: 658819 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.4760. Min Act: -0.0000

Data Index: 647933 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.4552. Min Act: -0.0000

Data Index: 643420 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.3975. Min Act: -0.0000

Data Index: 781151 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.3772. Min Act: -0.0000

Data Index: 1164750 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.4657. Min Act: -0.0000

Data Index: 807674 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.3499. Min Act: -0.0000

Data Index: 297717 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.3914. Min Act: -0.0000

Data Index: 619176 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.3918. Min Act: -0.0000

Data Index: 766380 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.2764. Min Act: -0.0000

Data Index: 498909 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.3875. Min Act: -0.0000

Data Index: 257068 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.3234. Min Act: -0.0000

Data Index: 188747 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.2095. Min Act: -0.0000

Data Index: 313378 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.3228. Min Act: -0.0000

Data Index: 225435 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 1.6774. Min Range: -1.6774

Max Act: 1.2544. Min Act: -0.0000

Data Index: 252666 (C4 (Web Text))

Max Activating Token Index: 75