Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1482 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1095. Min Range: -1.1095

Max Act: 1.0883. Min Act: -0.0001

Data Index: 222450 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 1.1095. Min Range: -1.1095

Max Act: 0.8686. Min Act: -0.0001

Data Index: 420320 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 1.1095. Min Range: -1.1095

Max Act: 0.9126. Min Act: -0.0001

Data Index: 830858 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 1.1095. Min Range: -1.1095

Max Act: 1.1095. Min Act: -0.0001

Data Index: 1006815 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 1.1095. Min Range: -1.1095

Max Act: 0.9305. Min Act: -0.0001

Data Index: 102436 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 1.1095. Min Range: -1.1095

Max Act: 1.0393. Min Act: -0.0001

Data Index: 48995 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 1.1095. Min Range: -1.1095

Max Act: 0.9107. Min Act: -0.0001

Data Index: 1056557 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 1.1095. Min Range: -1.1095

Max Act: 0.9324. Min Act: -0.0001

Data Index: 606130 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 1.1095. Min Range: -1.1095

Max Act: 0.9431. Min Act: -0.0001

Data Index: 425177 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 1.1095. Min Range: -1.1095

Max Act: 1.0426. Min Act: -0.0001

Data Index: 806722 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 1.1095. Min Range: -1.1095

Max Act: 0.9774. Min Act: -0.0001

Data Index: 748972 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 1.1095. Min Range: -1.1095

Max Act: 0.8510. Min Act: -0.0002

Data Index: 927991 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 1.1095. Min Range: -1.1095

Max Act: 0.8825. Min Act: -0.0001

Data Index: 1097123 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 1.1095. Min Range: -1.1095

Max Act: 1.0600. Min Act: -0.0001

Data Index: 1260740 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 1.1095. Min Range: -1.1095

Max Act: 0.9380. Min Act: -0.0001

Data Index: 189026 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 1.1095. Min Range: -1.1095

Max Act: 0.8110. Min Act: -0.0002

Data Index: 48620 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 1.1095. Min Range: -1.1095

Max Act: 0.9896. Min Act: -0.0001

Data Index: 591028 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 1.1095. Min Range: -1.1095

Max Act: 1.0673. Min Act: -0.0001

Data Index: 1163566 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 1.1095. Min Range: -1.1095

Max Act: 0.8734. Min Act: -0.0002

Data Index: 5171 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 1.1095. Min Range: -1.1095

Max Act: 1.0057. Min Act: -0.0002

Data Index: 804457 (C4 (Web Text))

Max Activating Token Index: 498