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

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

Neuron 3279 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: 0.1144. Min Range: -0.1144

Max Act: 0.1144. Min Act: -0.0000

Data Index: 27817 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1261560 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0946. Min Act: -0.0000

Data Index: 86425 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0903. Min Act: -0.0000

Data Index: 339391 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0875. Min Act: -0.0000

Data Index: 924667 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0896. Min Act: -0.0000

Data Index: 559344 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0822. Min Act: -0.0000

Data Index: 951479 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0854. Min Act: -0.0000

Data Index: 819791 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0811. Min Act: -0.0000

Data Index: 495958 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0802. Min Act: -0.0000

Data Index: 693968 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0775. Min Act: -0.0000

Data Index: 49326 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0776. Min Act: -0.0000

Data Index: 911070 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0784. Min Act: -0.0000

Data Index: 2191 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0773. Min Act: -0.0000

Data Index: 376656 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0771. Min Act: -0.0000

Data Index: 243181 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0708. Min Act: -0.0000

Data Index: 670454 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0733. Min Act: -0.0000

Data Index: 218508 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0721. Min Act: -0.0000

Data Index: 870315 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1345540 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0718. Min Act: -0.0000

Data Index: 1291617 (C4 (Web Text))

Max Activating Token Index: 452