Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1177 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0005

Data Index: 1163983 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0005

Data Index: 1599287 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0005

Data Index: 1483227 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0005

Data Index: 528373 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0005

Data Index: 561886 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0005

Data Index: 884303 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0517. Min Act: -0.0005

Data Index: 1445535 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0500. Min Act: -0.0005

Data Index: 417077 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0500. Min Act: -0.0005

Data Index: 800810 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0477. Min Act: -0.0005

Data Index: 103893 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0477. Min Act: -0.0005

Data Index: 52286 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0477. Min Act: -0.0005

Data Index: 505455 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0477. Min Act: -0.0005

Data Index: 342012 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0442. Min Act: -0.0005

Data Index: 968348 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0442. Min Act: -0.0005

Data Index: 213505 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0442. Min Act: -0.0005

Data Index: 263463 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0442. Min Act: -0.0005

Data Index: 424200 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0442. Min Act: -0.0005

Data Index: 761195 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0442. Min Act: -0.0005

Data Index: 10327 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0442. Min Act: -0.0005

Data Index: 534011 (C4 (Web Text))

Max Activating Token Index: 1