Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 581 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6900. Min Act: -0.0001

Data Index: 1129520 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6347. Min Act: -0.0000

Data Index: 205582 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6228. Min Act: -0.0000

Data Index: 949713 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5776. Min Act: -0.0001

Data Index: 752278 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1134381 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5801. Min Act: -0.0000

Data Index: 67150 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1188677 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5579. Min Act: -0.0001

Data Index: 488822 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5353. Min Act: -0.0000

Data Index: 319392 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5241. Min Act: -0.0000

Data Index: 683648 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5705. Min Act: -0.0000

Data Index: 1255921 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5082. Min Act: -0.0000

Data Index: 1064123 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1319462 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5048. Min Act: -0.0001

Data Index: 1250047 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.4851. Min Act: -0.0000

Data Index: 1053866 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5180. Min Act: -0.0000

Data Index: 832689 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.4508. Min Act: -0.0000

Data Index: 399588 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.4813. Min Act: -0.0000

Data Index: 667005 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.4786. Min Act: -0.0000

Data Index: 708313 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1250711 (C4 (Web Text))

Max Activating Token Index: 897