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

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

Neuron 1513 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: 2.6095. Min Range: -2.6095

Max Act: 2.4996. Min Act: -0.0000

Data Index: 367306 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 2.6095. Min Range: -2.6095

Max Act: 2.6095. Min Act: -0.0000

Data Index: 145854 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 2.6095. Min Range: -2.6095

Max Act: 2.4140. Min Act: -0.0000

Data Index: 1247622 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 2.6095. Min Range: -2.6095

Max Act: 2.0910. Min Act: -0.0000

Data Index: 507548 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.7228. Min Act: -0.0000

Data Index: 1122341 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.6107. Min Act: -0.0000

Data Index: 1058794 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.4783. Min Act: -0.0000

Data Index: 1276929 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.4525. Min Act: -0.0000

Data Index: 634983 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.4424. Min Act: -0.0000

Data Index: 150088 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.5158. Min Act: -0.0000

Data Index: 721419 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.4364. Min Act: -0.0000

Data Index: 193984 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.3886. Min Act: -0.0000

Data Index: 184237 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.3198. Min Act: -0.0000

Data Index: 1249837 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.4398. Min Act: -0.0000

Data Index: 759694 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.3142. Min Act: -0.0000

Data Index: 1327428 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.2826. Min Act: -0.0000

Data Index: 197587 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1466325 (Python Code)

Max Activating Token Index: 966

Text #17

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.2733. Min Act: -0.0000

Data Index: 525683 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.2287. Min Act: -0.0000

Data Index: 48830 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 2.6095. Min Range: -2.6095

Max Act: 1.2599. Min Act: -0.0000

Data Index: 13676 (C4 (Web Text))

Max Activating Token Index: 1021