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

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

Neuron 1913 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: 1.1921. Min Range: -1.1921

Max Act: 1.1921. Min Act: -0.0000

Data Index: 519832 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.9884. Min Act: -0.0001

Data Index: 198509 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 1.1921. Min Range: -1.1921

Max Act: 1.0137. Min Act: -0.0000

Data Index: 211240 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.9033. Min Act: -0.0000

Data Index: 504662 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.8387. Min Act: -0.0001

Data Index: 444674 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.8006. Min Act: -0.0001

Data Index: 712607 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1282127 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7907. Min Act: -0.0000

Data Index: 629243 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.8343. Min Act: -0.0001

Data Index: 837263 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1049811 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7494. Min Act: -0.0000

Data Index: 730342 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7647. Min Act: -0.0000

Data Index: 448243 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7551. Min Act: -0.0001

Data Index: 1080168 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7719. Min Act: -0.0000

Data Index: 638384 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1312112 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7365. Min Act: -0.0000

Data Index: 1176910 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.6918. Min Act: -0.0000

Data Index: 703211 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.6748. Min Act: -0.0000

Data Index: 158377 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1011109 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.6908. Min Act: -0.0000

Data Index: 965713 (C4 (Web Text))

Max Activating Token Index: 11