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

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

Neuron 464 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5079. Min Range: -1.5079

Max Act: 1.5079. Min Act: -0.0001

Data Index: 721741 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.5079. Min Range: -1.5079

Max Act: 1.3165. Min Act: -0.0001

Data Index: 522383 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 1.5079. Min Range: -1.5079

Max Act: 1.3759. Min Act: -0.0001

Data Index: 1182705 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 1.5079. Min Range: -1.5079

Max Act: 1.1715. Min Act: -0.0001

Data Index: 76385 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 1.5079. Min Range: -1.5079

Max Act: 1.2096. Min Act: -0.0001

Data Index: 708589 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 1.5079. Min Range: -1.5079

Max Act: 1.0535. Min Act: -0.0001

Data Index: 153500 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 1.5079. Min Range: -1.5079

Max Act: 1.0432. Min Act: -0.0001

Data Index: 896707 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 1.5079. Min Range: -1.5079

Max Act: 0.9649. Min Act: 0.0000

Data Index: 1328892 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 1.5079. Min Range: -1.5079

Max Act: 0.9609. Min Act: -0.0001

Data Index: 374077 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 1.5079. Min Range: -1.5079

Max Act: 0.9634. Min Act: -0.0001

Data Index: 1194221 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 1.5079. Min Range: -1.5079

Max Act: 0.9301. Min Act: -0.0001

Data Index: 1058293 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 1.5079. Min Range: -1.5079

Max Act: 0.8902. Min Act: -0.0001

Data Index: 1264344 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 1.5079. Min Range: -1.5079

Max Act: 0.8539. Min Act: -0.0001

Data Index: 1109867 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.5079. Min Range: -1.5079

Max Act: 0.8908. Min Act: -0.0001

Data Index: 1066786 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 1.5079. Min Range: -1.5079

Max Act: 0.9371. Min Act: -0.0001

Data Index: 933198 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 1.5079. Min Range: -1.5079

Max Act: 0.8893. Min Act: -0.0001

Data Index: 282288 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 1.5079. Min Range: -1.5079

Max Act: 0.8881. Min Act: -0.0000

Data Index: 768860 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.5079. Min Range: -1.5079

Max Act: 0.9474. Min Act: 0.0000

Data Index: 944923 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 1.5079. Min Range: -1.5079

Max Act: 0.8858. Min Act: -0.0001

Data Index: 977330 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 1.5079. Min Range: -1.5079

Max Act: 0.8583. Min Act: -0.0001

Data Index: 464492 (C4 (Web Text))

Max Activating Token Index: 210