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

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

Neuron 561 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0263. Min Range: -1.0263

Max Act: 1.0130. Min Act: -0.0000

Data Index: 1077688 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 1.0263. Min Range: -1.0263

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1581361 (Python Code)

Max Activating Token Index: 928

Text #2

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.9693. Min Act: -0.0000

Data Index: 574626 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.8918. Min Act: -0.0000

Data Index: 1189256 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.8351. Min Act: -0.0000

Data Index: 62959 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1166784 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1003627 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.8326. Min Act: -0.0000

Data Index: 955374 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.8715. Min Act: -0.0000

Data Index: 983890 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7892. Min Act: -0.0000

Data Index: 706653 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.8578. Min Act: -0.0000

Data Index: 1010806 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1348448 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7857. Min Act: -0.0000

Data Index: 892171 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7598. Min Act: -0.0000

Data Index: 819872 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7288. Min Act: -0.0000

Data Index: 271553 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.8318. Min Act: -0.0000

Data Index: 456173 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7773. Min Act: -0.0000

Data Index: 312799 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7342. Min Act: -0.0000

Data Index: 725232 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7804. Min Act: -0.0000

Data Index: 923983 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1124020 (C4 (Web Text))

Max Activating Token Index: 309