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

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

Neuron 4330 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.8008. Min Act: -0.0000

Data Index: 66907 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.6823. Min Act: -0.0000

Data Index: 583265 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.4487. Min Act: -0.0000

Data Index: 55689 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.4038. Min Act: -0.0000

Data Index: 211701 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.3440. Min Act: -0.0000

Data Index: 1180542 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.2488. Min Act: -0.0000

Data Index: 1055147 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.3127. Min Act: -0.0000

Data Index: 964101 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.2207. Min Act: -0.0000

Data Index: 893990 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.2226. Min Act: -0.0000

Data Index: 528040 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.2457. Min Act: -0.0000

Data Index: 547011 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.2490. Min Act: -0.0000

Data Index: 1357695 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.2323. Min Act: -0.0000

Data Index: 1154348 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.2550. Min Act: -0.0000

Data Index: 1014908 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.2145. Min Act: -0.0000

Data Index: 44613 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.2208. Min Act: -0.0000

Data Index: 1156499 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.1749. Min Act: -0.0000

Data Index: 1227191 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.1655. Min Act: -0.0000

Data Index: 220462 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.1860. Min Act: -0.0000

Data Index: 712874 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.2182. Min Act: -0.0000

Data Index: 106460 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 1.8008. Min Range: -1.8008

Max Act: 1.2091. Min Act: -0.0000

Data Index: 570855 (C4 (Web Text))

Max Activating Token Index: 566