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

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

Neuron 4694 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1619. Min Range: -2.1619

Max Act: 2.1619. Min Act: -0.0000

Data Index: 873671 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.8556. Min Act: -0.0000

Data Index: 948854 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.6982. Min Act: -0.0000

Data Index: 1098657 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.6177. Min Act: -0.0000

Data Index: 815987 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.5251. Min Act: -0.0000

Data Index: 137859 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.5340. Min Act: -0.0000

Data Index: 60940 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.5331. Min Act: -0.0000

Data Index: 390097 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.5392. Min Act: -0.0000

Data Index: 863985 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.5275. Min Act: -0.0000

Data Index: 1258523 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.4685. Min Act: -0.0000

Data Index: 712984 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.5089. Min Act: -0.0000

Data Index: 304684 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.4629. Min Act: -0.0000

Data Index: 599020 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.4930. Min Act: -0.0000

Data Index: 771634 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.4928. Min Act: -0.0000

Data Index: 1021542 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.4773. Min Act: -0.0000

Data Index: 571564 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.4366. Min Act: -0.0000

Data Index: 711656 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.5038. Min Act: -0.0000

Data Index: 118656 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.4541. Min Act: -0.0000

Data Index: 178125 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.4498. Min Act: -0.0000

Data Index: 949987 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 2.1619. Min Range: -2.1619

Max Act: 1.4396. Min Act: -0.0000

Data Index: 240508 (C4 (Web Text))

Max Activating Token Index: 201