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

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

Neuron 4967 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0407. Min Range: -2.0407

Max Act: 2.0407. Min Act: -0.0000

Data Index: 997827 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9055. Min Act: -0.0000

Data Index: 1454628 (Python Code)

Max Activating Token Index: 738

Text #2

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.8656. Min Act: -0.0000

Data Index: 1364358 (Python Code)

Max Activating Token Index: 490

Text #3

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.8496. Min Act: -0.0000

Data Index: 1364014 (Python Code)

Max Activating Token Index: 410

Text #4

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.8378. Min Act: -0.0000

Data Index: 1507841 (Python Code)

Max Activating Token Index: 280

Text #5

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.7925. Min Act: -0.0000

Data Index: 1385132 (Python Code)

Max Activating Token Index: 312

Text #6

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.6441. Min Act: -0.0000

Data Index: 1620399 (Python Code)

Max Activating Token Index: 733

Text #7

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.5079. Min Act: -0.0000

Data Index: 1648670 (Python Code)

Max Activating Token Index: 99

Text #8

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.5110. Min Act: -0.0000

Data Index: 1655790 (Python Code)

Max Activating Token Index: 314

Text #9

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.4444. Min Act: -0.0000

Data Index: 1524707 (Python Code)

Max Activating Token Index: 108

Text #10

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.4509. Min Act: -0.0000

Data Index: 613910 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.4068. Min Act: -0.0000

Data Index: 1634110 (Python Code)

Max Activating Token Index: 90

Text #12

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.4092. Min Act: -0.0000

Data Index: 1583232 (Python Code)

Max Activating Token Index: 779

Text #13

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.3658. Min Act: -0.0000

Data Index: 1480464 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.5256. Min Act: -0.0000

Data Index: 1548218 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.3811. Min Act: -0.0000

Data Index: 1194798 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.3790. Min Act: -0.0000

Data Index: 469926 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.4012. Min Act: -0.0000

Data Index: 1517820 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.3691. Min Act: -0.0000

Data Index: 1164793 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.4078. Min Act: -0.0000

Data Index: 1412945 (Python Code)

Max Activating Token Index: 52