Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 816 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.9789. Min Act: -0.0000

Data Index: 593243 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.7016. Min Act: -0.0000

Data Index: 311678 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1058537 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.7466. Min Act: -0.0000

Data Index: 472804 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.6806. Min Act: -0.0000

Data Index: 379285 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.6916. Min Act: -0.0000

Data Index: 118904 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.6744. Min Act: -0.0000

Data Index: 879700 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.6952. Min Act: -0.0000

Data Index: 581476 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1201429 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.6470. Min Act: -0.0000

Data Index: 310723 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1331929 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.5997. Min Act: -0.0000

Data Index: 528114 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.6901. Min Act: -0.0000

Data Index: 417968 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.5611. Min Act: -0.0000

Data Index: 183558 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.6111. Min Act: -0.0000

Data Index: 783619 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.6464. Min Act: -0.0000

Data Index: 261017 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.5647. Min Act: -0.0000

Data Index: 253296 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.6183. Min Act: -0.0000

Data Index: 950251 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.7076. Min Act: -0.0000

Data Index: 975341 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.9789. Min Range: -0.9789

Max Act: 0.5621. Min Act: -0.0000

Data Index: 143292 (C4 (Web Text))

Max Activating Token Index: 657