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

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

Neuron 4472 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.9709. Min Act: -0.0000

Data Index: 702251 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.9507. Min Act: -0.0000

Data Index: 594424 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.9074. Min Act: -0.0000

Data Index: 191481 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.7280. Min Act: -0.0000

Data Index: 1189239 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.7380. Min Act: -0.0000

Data Index: 831427 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.6190. Min Act: -0.0000

Data Index: 183698 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.6471. Min Act: -0.0000

Data Index: 326503 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.6938. Min Act: -0.0000

Data Index: 860052 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.5921. Min Act: -0.0000

Data Index: 194419 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.5746. Min Act: -0.0000

Data Index: 459137 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.5633. Min Act: -0.0000

Data Index: 113079 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.5137. Min Act: -0.0000

Data Index: 921877 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.5034. Min Act: -0.0000

Data Index: 357087 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.4928. Min Act: -0.0000

Data Index: 1063792 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.4775. Min Act: -0.0000

Data Index: 289521 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.4486. Min Act: -0.0000

Data Index: 973273 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.3070. Min Act: -0.0000

Data Index: 1268626 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.2027. Min Act: -0.0000

Data Index: 806380 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.1963. Min Act: -0.0000

Data Index: 1249348 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.2020. Min Act: -0.0000

Data Index: 346831 (C4 (Web Text))

Max Activating Token Index: 951