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

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

Neuron 4611 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: 0.6002. Min Range: -0.6002

Max Act: 0.6002. Min Act: -0.0000

Data Index: 107969 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.5986. Min Act: -0.0000

Data Index: 726975 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1144935 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.5100. Min Act: -0.0000

Data Index: 399788 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4788. Min Act: -0.0000

Data Index: 124777 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4855. Min Act: -0.0001

Data Index: 915048 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4799. Min Act: -0.0000

Data Index: 358371 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4700. Min Act: -0.0000

Data Index: 376271 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4581. Min Act: -0.0000

Data Index: 801883 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4789. Min Act: -0.0000

Data Index: 959007 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4247. Min Act: -0.0000

Data Index: 492664 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.3932. Min Act: -0.0000

Data Index: 47592 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4181. Min Act: -0.0000

Data Index: 1311891 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1095536 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1052636 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4084. Min Act: -0.0000

Data Index: 739632 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1181603 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.3981. Min Act: -0.0000

Data Index: 379537 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.3613. Min Act: -0.0001

Data Index: 50406 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.3780. Min Act: -0.0000

Data Index: 762136 (C4 (Web Text))

Max Activating Token Index: 391