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

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

Neuron 1397 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1105. Min Range: -2.1105

Max Act: 2.1105. Min Act: -0.0000

Data Index: 1081082 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.9079. Min Act: -0.0000

Data Index: 17772 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.9632. Min Act: -0.0000

Data Index: 548799 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.8427. Min Act: -0.0000

Data Index: 486121 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.9442. Min Act: -0.0000

Data Index: 153972 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.8432. Min Act: -0.0000

Data Index: 306267 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.8296. Min Act: -0.0000

Data Index: 360072 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.7939. Min Act: -0.0000

Data Index: 1160831 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.8938. Min Act: -0.0000

Data Index: 1318586 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.7811. Min Act: -0.0000

Data Index: 477342 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.8759. Min Act: -0.0000

Data Index: 1236612 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.8535. Min Act: -0.0000

Data Index: 487669 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.7344. Min Act: -0.0000

Data Index: 956692 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.5556. Min Act: -0.0000

Data Index: 579797 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.6598. Min Act: -0.0000

Data Index: 766466 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.7268. Min Act: -0.0000

Data Index: 144391 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.7135. Min Act: -0.0000

Data Index: 7130 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.5884. Min Act: -0.0000

Data Index: 1131807 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.7836. Min Act: -0.0000

Data Index: 76926 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 2.1105. Min Range: -2.1105

Max Act: 1.6716. Min Act: -0.0000

Data Index: 127439 (C4 (Web Text))

Max Activating Token Index: 48