Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1281 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1279. Min Act: -0.0001

Data Index: 555606 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1015. Min Act: -0.0001

Data Index: 586052 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1331829 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0912. Min Act: -0.0001

Data Index: 594947 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0906. Min Act: -0.0001

Data Index: 204284 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0868. Min Act: -0.0001

Data Index: 918218 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0903. Min Act: -0.0001

Data Index: 107694 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0835. Min Act: -0.0001

Data Index: 441033 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0792. Min Act: -0.0001

Data Index: 415501 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0852. Min Act: -0.0001

Data Index: 702148 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0728. Min Act: -0.0001

Data Index: 853928 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0728. Min Act: -0.0001

Data Index: 334352 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0863. Min Act: -0.0001

Data Index: 920434 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0869. Min Act: -0.0001

Data Index: 430665 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1037531 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0825. Min Act: -0.0001

Data Index: 302757 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1275550 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0745. Min Act: -0.0001

Data Index: 467741 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0847. Min Act: -0.0001

Data Index: 820431 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0777. Min Act: -0.0001

Data Index: 507477 (C4 (Web Text))

Max Activating Token Index: 147