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

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

Neuron 167 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.3887. Min Act: -0.0000

Data Index: 446063 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.3462. Min Act: -0.0000

Data Index: 1025267 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.3094. Min Act: -0.0000

Data Index: 733196 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.1582. Min Act: -0.0000

Data Index: 282939 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.1270. Min Act: -0.0000

Data Index: 512572 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.1710. Min Act: -0.0000

Data Index: 615024 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.1363. Min Act: -0.0000

Data Index: 226287 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.2333. Min Act: -0.0000

Data Index: 724552 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.1400. Min Act: -0.0000

Data Index: 1164767 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.1210. Min Act: -0.0000

Data Index: 1183879 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.1084. Min Act: -0.0000

Data Index: 451631 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.1208. Min Act: -0.0000

Data Index: 285412 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.0593. Min Act: -0.0000

Data Index: 873863 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.0340. Min Act: -0.0000

Data Index: 1253539 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.0919. Min Act: -0.0000

Data Index: 354178 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.0430. Min Act: -0.0000

Data Index: 578305 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 1.3887. Min Range: -1.3887

Max Act: 1.0081. Min Act: -0.0000

Data Index: 997818 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 1.3887. Min Range: -1.3887

Max Act: 0.9782. Min Act: -0.0000

Data Index: 281351 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.3887. Min Range: -1.3887

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1068731 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 1.3887. Min Range: -1.3887

Max Act: 0.9638. Min Act: -0.0000

Data Index: 840181 (C4 (Web Text))

Max Activating Token Index: 237