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

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

Neuron 5740 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4869. Min Range: -2.4869

Max Act: 2.4869. Min Act: -0.0000

Data Index: 882477 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 2.4869. Min Range: -2.4869

Max Act: 2.2087. Min Act: -0.0000

Data Index: 14042 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 2.4869. Min Range: -2.4869

Max Act: 2.1638. Min Act: -0.0000

Data Index: 48535 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 2.4869. Min Range: -2.4869

Max Act: 2.1215. Min Act: -0.0000

Data Index: 1241345 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 2.4869. Min Range: -2.4869

Max Act: 2.0064. Min Act: -0.0000

Data Index: 1284154 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 2.4869. Min Range: -2.4869

Max Act: 1.9645. Min Act: -0.0000

Data Index: 292460 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 2.4869. Min Range: -2.4869

Max Act: 1.7526. Min Act: -0.0000

Data Index: 616378 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 2.4869. Min Range: -2.4869

Max Act: 1.8389. Min Act: -0.0000

Data Index: 620810 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 2.4869. Min Range: -2.4869

Max Act: 2.0413. Min Act: -0.0000

Data Index: 632007 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 2.4869. Min Range: -2.4869

Max Act: 1.8212. Min Act: -0.0000

Data Index: 922172 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 2.4869. Min Range: -2.4869

Max Act: 1.9264. Min Act: -0.0000

Data Index: 607151 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 2.4869. Min Range: -2.4869

Max Act: 1.8050. Min Act: -0.0000

Data Index: 1047730 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 2.4869. Min Range: -2.4869

Max Act: 1.7959. Min Act: -0.0000

Data Index: 32787 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 2.4869. Min Range: -2.4869

Max Act: 1.9134. Min Act: -0.0000

Data Index: 133001 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 2.4869. Min Range: -2.4869

Max Act: 1.8989. Min Act: -0.0000

Data Index: 986208 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 2.4869. Min Range: -2.4869

Max Act: 1.8810. Min Act: -0.0000

Data Index: 1122 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 2.4869. Min Range: -2.4869

Max Act: 1.7716. Min Act: -0.0000

Data Index: 1134603 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 2.4869. Min Range: -2.4869

Max Act: 1.8866. Min Act: -0.0000

Data Index: 308530 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 2.4869. Min Range: -2.4869

Max Act: 1.8650. Min Act: -0.0000

Data Index: 937248 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 2.4869. Min Range: -2.4869

Max Act: 1.8796. Min Act: -0.0000

Data Index: 145429 (C4 (Web Text))

Max Activating Token Index: 554