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

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

Neuron 540 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.8313. Min Act: -0.0000

Data Index: 1553520 (Python Code)

Max Activating Token Index: 345

Text #1

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.5221. Min Act: -0.0000

Data Index: 1418623 (Python Code)

Max Activating Token Index: 206

Text #2

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.6101. Min Act: -0.0000

Data Index: 1516643 (Python Code)

Max Activating Token Index: 796

Text #3

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.1586. Min Act: -0.0000

Data Index: 1506015 (Python Code)

Max Activating Token Index: 428

Text #4

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.4932. Min Act: -0.0000

Data Index: 1644025 (Python Code)

Max Activating Token Index: 200

Text #5

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.2781. Min Act: -0.0000

Data Index: 1509698 (Python Code)

Max Activating Token Index: 851

Text #6

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.2952. Min Act: -0.0000

Data Index: 1618873 (Python Code)

Max Activating Token Index: 455

Text #7

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.2083. Min Act: -0.0000

Data Index: 1573156 (Python Code)

Max Activating Token Index: 121

Text #8

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.1765. Min Act: -0.0000

Data Index: 1450023 (Python Code)

Max Activating Token Index: 296

Text #9

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.2973. Min Act: -0.0000

Data Index: 1551330 (Python Code)

Max Activating Token Index: 88

Text #10

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.1580. Min Act: -0.0000

Data Index: 1536616 (Python Code)

Max Activating Token Index: 563

Text #11

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.0000. Min Act: -0.0000

Data Index: 1423308 (Python Code)

Max Activating Token Index: 715

Text #12

Max Range: 2.8313. Min Range: -2.8313

Max Act: 1.9122. Min Act: -0.0000

Data Index: 1546261 (Python Code)

Max Activating Token Index: 895

Text #13

Max Range: 2.8313. Min Range: -2.8313

Max Act: 1.9607. Min Act: -0.0000

Data Index: 1488479 (Python Code)

Max Activating Token Index: 894

Text #14

Max Range: 2.8313. Min Range: -2.8313

Max Act: 1.9342. Min Act: -0.0000

Data Index: 1577884 (Python Code)

Max Activating Token Index: 802

Text #15

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.0422. Min Act: -0.0000

Data Index: 1577898 (Python Code)

Max Activating Token Index: 800

Text #16

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.1339. Min Act: -0.0000

Data Index: 1448391 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.1370. Min Act: -0.0000

Data Index: 1549483 (Python Code)

Max Activating Token Index: 227

Text #18

Max Range: 2.8313. Min Range: -2.8313

Max Act: 2.0036. Min Act: -0.0000

Data Index: 1508423 (Python Code)

Max Activating Token Index: 847

Text #19

Max Range: 2.8313. Min Range: -2.8313

Max Act: 1.8531. Min Act: -0.0000

Data Index: 1605373 (Python Code)

Max Activating Token Index: 389