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

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

Neuron 1328 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2913. Min Range: -1.2913

Max Act: 1.2913. Min Act: -0.0001

Data Index: 77264 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 1.2913. Min Range: -1.2913

Max Act: 1.0100. Min Act: -0.0001

Data Index: 1041857 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.9944. Min Act: -0.0001

Data Index: 649815 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.9057. Min Act: -0.0001

Data Index: 217960 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 1.2913. Min Range: -1.2913

Max Act: 1.0050. Min Act: -0.0001

Data Index: 993785 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.9494. Min Act: -0.0001

Data Index: 559563 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.9790. Min Act: -0.0001

Data Index: 370360 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.8704. Min Act: -0.0001

Data Index: 347304 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.7966. Min Act: -0.0001

Data Index: 657775 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.8406. Min Act: -0.0001

Data Index: 1204976 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.8467. Min Act: -0.0001

Data Index: 574812 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.8195. Min Act: -0.0001

Data Index: 745425 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.8119. Min Act: -0.0001

Data Index: 69896 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.8113. Min Act: -0.0001

Data Index: 964820 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.8071. Min Act: -0.0001

Data Index: 1300729 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.7441. Min Act: -0.0001

Data Index: 159717 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.7975. Min Act: -0.0001

Data Index: 1025141 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.8079. Min Act: -0.0001

Data Index: 1045156 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.8033. Min Act: -0.0001

Data Index: 227393 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 1.2913. Min Range: -1.2913

Max Act: 0.7996. Min Act: -0.0001

Data Index: 982439 (C4 (Web Text))

Max Activating Token Index: 726