Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 690 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.9530. Min Act: -0.0000

Data Index: 1253804 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.7790. Min Act: -0.0000

Data Index: 918260 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.6412. Min Act: -0.0000

Data Index: 773671 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.4363. Min Act: -0.0000

Data Index: 274078 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.3979. Min Act: -0.0000

Data Index: 467632 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.3557. Min Act: -0.0000

Data Index: 1123127 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1134470 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.3098. Min Act: -0.0000

Data Index: 475650 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.3692. Min Act: -0.0000

Data Index: 15373 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.2741. Min Act: -0.0000

Data Index: 874771 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.2679. Min Act: -0.0000

Data Index: 143399 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.2760. Min Act: -0.0000

Data Index: 871652 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.1833. Min Act: -0.0000

Data Index: 1237740 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.1611. Min Act: -0.0000

Data Index: 405989 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.3077. Min Act: -0.0001

Data Index: 83772 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.2149. Min Act: -0.0000

Data Index: 174688 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.2841. Min Act: -0.0000

Data Index: 61256 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.1985. Min Act: 0.0000

Data Index: 981540 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.1617. Min Act: -0.0000

Data Index: 1101865 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.2255. Min Act: -0.0000

Data Index: 1066612 (C4 (Web Text))

Max Activating Token Index: 382