Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1233 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1428. Min Range: -1.1428

Max Act: 1.1428. Min Act: -0.0000

Data Index: 124503 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 1.1428. Min Range: -1.1428

Max Act: 1.0337. Min Act: -0.0000

Data Index: 1170868 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 1.1428. Min Range: -1.1428

Max Act: 1.0184. Min Act: -0.0000

Data Index: 1361151 (Python Code)

Max Activating Token Index: 995

Text #3

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.9101. Min Act: -0.0000

Data Index: 970247 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1399325 (Python Code)

Max Activating Token Index: 502

Text #5

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1581250 (Python Code)

Max Activating Token Index: 405

Text #6

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1060160 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.7707. Min Act: -0.0000

Data Index: 1588448 (Python Code)

Max Activating Token Index: 556

Text #8

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1425214 (Python Code)

Max Activating Token Index: 850

Text #9

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.7765. Min Act: -0.0000

Data Index: 632595 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1320739 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.7073. Min Act: -0.0000

Data Index: 59337 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1206414 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1395500 (Python Code)

Max Activating Token Index: 426

Text #14

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.6682. Min Act: -0.0000

Data Index: 366053 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.6580. Min Act: -0.0000

Data Index: 880526 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1620716 (Python Code)

Max Activating Token Index: 950

Text #17

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.7286. Min Act: -0.0000

Data Index: 656528 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.6484. Min Act: -0.0000

Data Index: 1012617 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.6976. Min Act: -0.0000

Data Index: 129776 (C4 (Web Text))

Max Activating Token Index: 68