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

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

Neuron 206 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0810. Min Act: -0.0001

Data Index: 719348 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9456. Min Act: -0.0000

Data Index: 403654 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9036. Min Act: -0.0000

Data Index: 427352 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.7886. Min Act: -0.0001

Data Index: 248589 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8349. Min Act: -0.0000

Data Index: 704148 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8822. Min Act: -0.0001

Data Index: 659836 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8056. Min Act: -0.0000

Data Index: 897307 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.7766. Min Act: -0.0001

Data Index: 1032747 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.7462. Min Act: -0.0000

Data Index: 981841 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.7914. Min Act: -0.0000

Data Index: 708675 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8069. Min Act: -0.0001

Data Index: 299129 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.7681. Min Act: -0.0001

Data Index: 1337541 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.7140. Min Act: -0.0001

Data Index: 874147 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.7531. Min Act: -0.0001

Data Index: 1017751 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.7220. Min Act: -0.0001

Data Index: 654984 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.7312. Min Act: -0.0001

Data Index: 308065 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.6498. Min Act: -0.0001

Data Index: 407717 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1091323 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.6595. Min Act: -0.0000

Data Index: 525939 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.6748. Min Act: -0.0000

Data Index: 642407 (C4 (Web Text))

Max Activating Token Index: 445