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

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

Neuron 1157 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2455. Min Act: -0.0000

Data Index: 838840 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2162. Min Act: -0.0000

Data Index: 373749 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1054596 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1135921 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1942. Min Act: -0.0000

Data Index: 65535 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2121. Min Act: -0.0000

Data Index: 236294 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1907. Min Act: -0.0000

Data Index: 886211 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1869. Min Act: -0.0000

Data Index: 794099 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1300886 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1875. Min Act: -0.0000

Data Index: 517762 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1939. Min Act: -0.0000

Data Index: 575390 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1860. Min Act: -0.0000

Data Index: 998725 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1735. Min Act: -0.0000

Data Index: 767619 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1786. Min Act: -0.0000

Data Index: 854747 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1761. Min Act: -0.0000

Data Index: 815474 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1693. Min Act: -0.0000

Data Index: 660115 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1636. Min Act: -0.0000

Data Index: 224396 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1663. Min Act: -0.0000

Data Index: 874424 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1569. Min Act: -0.0000

Data Index: 802297 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1620. Min Act: -0.0000

Data Index: 456568 (C4 (Web Text))

Max Activating Token Index: 995