Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3913 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.6075. Min Act: -0.0000

Data Index: 135232 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.9840. Min Act: -0.0000

Data Index: 430364 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 2.6075. Min Range: -2.6075

Max Act: 2.0857. Min Act: -0.0000

Data Index: 559592 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.8948. Min Act: -0.0000

Data Index: 1182913 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.7704. Min Act: -0.0000

Data Index: 8568 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.7637. Min Act: -0.0000

Data Index: 767231 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.7710. Min Act: -0.0000

Data Index: 1071278 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.7231. Min Act: -0.0000

Data Index: 730855 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.6494. Min Act: -0.0000

Data Index: 370570 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.6458. Min Act: -0.0000

Data Index: 1354703 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.6920. Min Act: -0.0000

Data Index: 246723 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.6682. Min Act: -0.0000

Data Index: 938046 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.6598. Min Act: -0.0000

Data Index: 1295668 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.6501. Min Act: -0.0000

Data Index: 298126 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.5308. Min Act: -0.0000

Data Index: 1251412 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.5137. Min Act: -0.0000

Data Index: 497776 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.5201. Min Act: -0.0000

Data Index: 957449 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.6026. Min Act: -0.0000

Data Index: 198548 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.8598. Min Act: -0.0000

Data Index: 135834 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 2.6075. Min Range: -2.6075

Max Act: 1.5734. Min Act: -0.0000

Data Index: 718860 (C4 (Web Text))

Max Activating Token Index: 333