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

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

Neuron 3740 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0465. Min Range: -2.0465

Max Act: 2.0465. Min Act: -0.0000

Data Index: 1065007 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.6837. Min Act: -0.0000

Data Index: 5643 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.4043. Min Act: -0.0000

Data Index: 768012 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.5372. Min Act: -0.0000

Data Index: 78482 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.6797. Min Act: -0.0001

Data Index: 1641609 (Python Code)

Max Activating Token Index: 262

Text #5

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.5728. Min Act: -0.0000

Data Index: 820856 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.5347. Min Act: -0.0000

Data Index: 404657 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.4639. Min Act: -0.0000

Data Index: 654359 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.4825. Min Act: -0.0001

Data Index: 367441 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.3554. Min Act: -0.0000

Data Index: 387753 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.5016. Min Act: -0.0000

Data Index: 373514 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.5344. Min Act: -0.0000

Data Index: 361946 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.4911. Min Act: -0.0000

Data Index: 32724 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.3439. Min Act: -0.0001

Data Index: 995685 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.4910. Min Act: -0.0000

Data Index: 676836 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.5298. Min Act: -0.0000

Data Index: 1034120 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.4204. Min Act: -0.0001

Data Index: 486726 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.4057. Min Act: -0.0000

Data Index: 907863 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.4340. Min Act: -0.0000

Data Index: 977967 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 2.0465. Min Range: -2.0465

Max Act: 1.4286. Min Act: -0.0000

Data Index: 953506 (C4 (Web Text))

Max Activating Token Index: 262