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

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

Neuron 97 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.5811. Min Act: -0.0000

Data Index: 18306 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.5482. Min Act: -0.0000

Data Index: 359784 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.5411. Min Act: -0.0000

Data Index: 595378 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1068478 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.5056. Min Act: -0.0000

Data Index: 630693 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1237554 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1125904 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1109851 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4372. Min Act: -0.0000

Data Index: 722208 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4656. Min Act: -0.0000

Data Index: 394065 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4172. Min Act: -0.0000

Data Index: 993278 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4077. Min Act: -0.0000

Data Index: 223307 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4148. Min Act: -0.0000

Data Index: 560193 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4002. Min Act: -0.0000

Data Index: 74127 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4073. Min Act: -0.0000

Data Index: 858126 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1288190 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3753. Min Act: -0.0000

Data Index: 188224 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3776. Min Act: -0.0000

Data Index: 683804 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3563. Min Act: -0.0000

Data Index: 28257 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3527. Min Act: -0.0000

Data Index: 395649 (C4 (Web Text))

Max Activating Token Index: 271