Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3671 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1438901 (Python Code)

Max Activating Token Index: 220

Text #1

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1571120 (Python Code)

Max Activating Token Index: 125

Text #2

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1633983 (Python Code)

Max Activating Token Index: 922

Text #3

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.8377. Min Act: -0.0000

Data Index: 1537991 (Python Code)

Max Activating Token Index: 281

Text #4

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1556266 (Python Code)

Max Activating Token Index: 489

Text #5

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1437306 (Python Code)

Max Activating Token Index: 319

Text #6

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.7811. Min Act: -0.0001

Data Index: 1517065 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1529042 (Python Code)

Max Activating Token Index: 650

Text #8

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.7895. Min Act: -0.0000

Data Index: 1371709 (Python Code)

Max Activating Token Index: 208

Text #9

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1617007 (Python Code)

Max Activating Token Index: 941

Text #10

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1561608 (Python Code)

Max Activating Token Index: 428

Text #11

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1385322 (Python Code)

Max Activating Token Index: 18

Text #12

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.7554. Min Act: -0.0000

Data Index: 1656112 (Python Code)

Max Activating Token Index: 266

Text #13

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.7615. Min Act: -0.0000

Data Index: 1656385 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1365131 (Python Code)

Max Activating Token Index: 387

Text #15

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1479018 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.6667. Min Act: -0.0001

Data Index: 1494318 (Python Code)

Max Activating Token Index: 603

Text #17

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.6831. Min Act: -0.0001

Data Index: 1418421 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1515641 (Python Code)

Max Activating Token Index: 114

Text #19

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1404685 (Python Code)

Max Activating Token Index: 794