Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1338 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.2048. Min Act: -0.0001

Data Index: 1279936 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1853. Min Act: -0.0001

Data Index: 179342 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1803. Min Act: -0.0001

Data Index: 202677 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1731. Min Act: -0.0001

Data Index: 105440 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1802. Min Act: -0.0001

Data Index: 799461 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1804. Min Act: -0.0001

Data Index: 1208399 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1683. Min Act: -0.0001

Data Index: 1009257 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1626. Min Act: -0.0001

Data Index: 999227 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1604. Min Act: -0.0001

Data Index: 1143207 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1733. Min Act: -0.0001

Data Index: 632385 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1579. Min Act: -0.0001

Data Index: 1569066 (Python Code)

Max Activating Token Index: 628

Text #11

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1754. Min Act: -0.0001

Data Index: 1082182 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1579. Min Act: -0.0001

Data Index: 131177 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1470. Min Act: -0.0001

Data Index: 370946 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1742. Min Act: -0.0001

Data Index: 1151263 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1583. Min Act: -0.0001

Data Index: 264210 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1604. Min Act: -0.0001

Data Index: 167917 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1063218 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1563. Min Act: -0.0001

Data Index: 531890 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1504. Min Act: -0.0001

Data Index: 592734 (C4 (Web Text))

Max Activating Token Index: 241