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

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

Neuron 3854 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6802. Min Range: -3.6802

Max Act: 3.6802. Min Act: -0.0001

Data Index: 1387678 (Python Code)

Max Activating Token Index: 1014

Text #1

Max Range: 3.6802. Min Range: -3.6802

Max Act: 3.3626. Min Act: -0.0001

Data Index: 1637647 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 3.6802. Min Range: -3.6802

Max Act: 3.2855. Min Act: -0.0001

Data Index: 1473034 (Python Code)

Max Activating Token Index: 1011

Text #3

Max Range: 3.6802. Min Range: -3.6802

Max Act: 3.2730. Min Act: -0.0001

Data Index: 1523825 (Python Code)

Max Activating Token Index: 856

Text #4

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.9052. Min Act: -0.0001

Data Index: 1426735 (Python Code)

Max Activating Token Index: 823

Text #5

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.8769. Min Act: -0.0001

Data Index: 1571462 (Python Code)

Max Activating Token Index: 659

Text #6

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.9123. Min Act: -0.0001

Data Index: 1471337 (Python Code)

Max Activating Token Index: 965

Text #7

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.8998. Min Act: -0.0000

Data Index: 1453227 (Python Code)

Max Activating Token Index: 560

Text #8

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.8154. Min Act: -0.0001

Data Index: 1560041 (Python Code)

Max Activating Token Index: 254

Text #9

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.8638. Min Act: -0.0001

Data Index: 1435764 (Python Code)

Max Activating Token Index: 448

Text #10

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.5677. Min Act: -0.0001

Data Index: 1583678 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.6112. Min Act: -0.0001

Data Index: 1404153 (Python Code)

Max Activating Token Index: 815

Text #12

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.6166. Min Act: -0.0001

Data Index: 1528453 (Python Code)

Max Activating Token Index: 145

Text #13

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.6002. Min Act: -0.0000

Data Index: 1527689 (Python Code)

Max Activating Token Index: 971

Text #14

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.4452. Min Act: -0.0001

Data Index: 1406392 (Python Code)

Max Activating Token Index: 619

Text #15

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.5600. Min Act: -0.0000

Data Index: 1544431 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.3946. Min Act: -0.0001

Data Index: 1385467 (Python Code)

Max Activating Token Index: 301

Text #17

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.4824. Min Act: -0.0001

Data Index: 1480957 (Python Code)

Max Activating Token Index: 886

Text #18

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.3649. Min Act: -0.0001

Data Index: 1619570 (Python Code)

Max Activating Token Index: 109

Text #19

Max Range: 3.6802. Min Range: -3.6802

Max Act: 2.4758. Min Act: -0.0001

Data Index: 1610824 (Python Code)

Max Activating Token Index: 85