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

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

Neuron 543 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1134. Min Range: -2.1134

Max Act: 2.1134. Min Act: -0.0000

Data Index: 137559 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.5716. Min Act: -0.0000

Data Index: 1055512 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.7706. Min Act: -0.0000

Data Index: 1296491 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.5327. Min Act: -0.0000

Data Index: 1159632 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.3796. Min Act: -0.0000

Data Index: 720570 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.5638. Min Act: -0.0000

Data Index: 867647 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.4272. Min Act: -0.0000

Data Index: 381321 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.4725. Min Act: -0.0000

Data Index: 878286 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.5059. Min Act: -0.0000

Data Index: 478577 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.3788. Min Act: -0.0000

Data Index: 820640 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.4780. Min Act: -0.0000

Data Index: 954797 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.4610. Min Act: -0.0000

Data Index: 1364692 (Python Code)

Max Activating Token Index: 174

Text #12

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.3906. Min Act: -0.0000

Data Index: 371235 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.5448. Min Act: -0.0000

Data Index: 582129 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.4409. Min Act: -0.0000

Data Index: 45825 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.5196. Min Act: -0.0000

Data Index: 626400 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.2908. Min Act: -0.0000

Data Index: 1001283 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.3901. Min Act: -0.0000

Data Index: 1014790 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.2993. Min Act: -0.0000

Data Index: 842010 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 2.1134. Min Range: -2.1134

Max Act: 1.4699. Min Act: -0.0000

Data Index: 451109 (C4 (Web Text))

Max Activating Token Index: 374