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

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

Neuron 2088 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1543042 (Python Code)

Max Activating Token Index: 525

Text #1

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1503436 (Python Code)

Max Activating Token Index: 212

Text #2

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1045866 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1633864 (Python Code)

Max Activating Token Index: 764

Text #4

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1516325 (Python Code)

Max Activating Token Index: 293

Text #5

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1539609 (Python Code)

Max Activating Token Index: 995

Text #6

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5608. Min Act: -0.0000

Data Index: 180390 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1499632 (Python Code)

Max Activating Token Index: 1000

Text #8

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5637. Min Act: -0.0000

Data Index: 370200 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1360870 (Python Code)

Max Activating Token Index: 994

Text #10

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1486172 (Python Code)

Max Activating Token Index: 590

Text #11

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1233117 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1606601 (Python Code)

Max Activating Token Index: 952

Text #13

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1633215 (Python Code)

Max Activating Token Index: 977

Text #14

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1360588 (Python Code)

Max Activating Token Index: 668

Text #15

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1406320 (Python Code)

Max Activating Token Index: 103

Text #16

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5097. Min Act: -0.0000

Data Index: 399119 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1587649 (Python Code)

Max Activating Token Index: 458

Text #18

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1649544 (Python Code)

Max Activating Token Index: 739

Text #19

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1501410 (Python Code)

Max Activating Token Index: 643