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

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

Neuron 2830 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: 0.1392. Min Range: -0.1392

Max Act: 0.1392. Min Act: -0.0001

Data Index: 1250318 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1244. Min Act: -0.0001

Data Index: 87473 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1188. Min Act: -0.0001

Data Index: 614639 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1162. Min Act: -0.0001

Data Index: 351322 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1103. Min Act: -0.0001

Data Index: 538699 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1040. Min Act: -0.0001

Data Index: 957233 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1112. Min Act: -0.0001

Data Index: 637809 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0985. Min Act: -0.0001

Data Index: 782429 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1019. Min Act: -0.0001

Data Index: 1346513 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0979. Min Act: -0.0001

Data Index: 259911 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0866. Min Act: -0.0001

Data Index: 709403 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0923. Min Act: -0.0001

Data Index: 895643 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0883. Min Act: -0.0001

Data Index: 428883 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0874. Min Act: -0.0001

Data Index: 1318292 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0825. Min Act: -0.0001

Data Index: 35461 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0800. Min Act: -0.0001

Data Index: 150535 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0836. Min Act: -0.0001

Data Index: 805555 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0834. Min Act: -0.0001

Data Index: 1090199 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0845. Min Act: -0.0001

Data Index: 1351164 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.0803. Min Act: -0.0001

Data Index: 453295 (C4 (Web Text))

Max Activating Token Index: 98