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

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

Neuron 2068 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.8087. Min Act: -0.0000

Data Index: 769835 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1252672 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7585. Min Act: -0.0000

Data Index: 899542 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7733. Min Act: -0.0000

Data Index: 869062 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6952. Min Act: -0.0000

Data Index: 291901 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7102. Min Act: -0.0000

Data Index: 770285 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6813. Min Act: -0.0000

Data Index: 27909 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6390. Min Act: -0.0000

Data Index: 802402 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6632. Min Act: -0.0000

Data Index: 243863 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1192263 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6262. Min Act: -0.0000

Data Index: 999767 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6428. Min Act: -0.0000

Data Index: 668963 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6399. Min Act: -0.0000

Data Index: 318530 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6381. Min Act: -0.0000

Data Index: 389735 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6374. Min Act: -0.0000

Data Index: 377284 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6345. Min Act: -0.0000

Data Index: 656625 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6332. Min Act: 0.0000

Data Index: 1277013 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6697. Min Act: -0.0000

Data Index: 12924 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6042. Min Act: -0.0000

Data Index: 794208 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6233. Min Act: -0.0000

Data Index: 530614 (C4 (Web Text))

Max Activating Token Index: 470