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

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

Neuron 488 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5130. Min Range: -2.5130

Max Act: 2.5130. Min Act: -0.0000

Data Index: 613156 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 2.5130. Min Range: -2.5130

Max Act: 2.1501. Min Act: -0.0000

Data Index: 142484 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.8856. Min Act: -0.0000

Data Index: 421614 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.9623. Min Act: -0.0000

Data Index: 120468 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.8131. Min Act: -0.0000

Data Index: 610084 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.6986. Min Act: -0.0000

Data Index: 1302127 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.6758. Min Act: -0.0000

Data Index: 546687 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.5745. Min Act: -0.0000

Data Index: 275742 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.6317. Min Act: -0.0000

Data Index: 1351177 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.4189. Min Act: -0.0000

Data Index: 115322 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.4213. Min Act: -0.0000

Data Index: 308316 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.4776. Min Act: -0.0000

Data Index: 475412 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.5784. Min Act: -0.0000

Data Index: 990217 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.4635. Min Act: -0.0000

Data Index: 922238 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.3276. Min Act: -0.0000

Data Index: 1076290 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.4043. Min Act: -0.0000

Data Index: 193393 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1495718 (Python Code)

Max Activating Token Index: 988

Text #17

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.2766. Min Act: -0.0000

Data Index: 1004413 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.2931. Min Act: -0.0000

Data Index: 455568 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 2.5130. Min Range: -2.5130

Max Act: 1.1359. Min Act: -0.0000

Data Index: 987258 (C4 (Web Text))

Max Activating Token Index: 747