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

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

Neuron 5666 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.6571. Min Act: -0.0000

Data Index: 433629 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.5131. Min Act: -0.0000

Data Index: 823436 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.6050. Min Act: -0.0000

Data Index: 881285 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.5843. Min Act: -0.0000

Data Index: 895828 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.7016. Min Act: -0.0000

Data Index: 1142506 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.3316. Min Act: -0.0000

Data Index: 738451 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.3882. Min Act: -0.0000

Data Index: 548410 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.3974. Min Act: -0.0000

Data Index: 516774 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.3851. Min Act: -0.0000

Data Index: 866177 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.4106. Min Act: -0.0000

Data Index: 1069828 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.3467. Min Act: -0.0001

Data Index: 437619 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.3080. Min Act: -0.0000

Data Index: 998929 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.4255. Min Act: -0.0000

Data Index: 1051431 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.3072. Min Act: -0.0000

Data Index: 1164302 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.3211. Min Act: -0.0000

Data Index: 1289107 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.2917. Min Act: -0.0000

Data Index: 1086888 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.4307. Min Act: -0.0000

Data Index: 542052 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.3803. Min Act: -0.0001

Data Index: 990602 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.1553. Min Act: -0.0000

Data Index: 1147836 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 2.7016. Min Range: -2.7016

Max Act: 2.1335. Min Act: -0.0001

Data Index: 1005465 (C4 (Web Text))

Max Activating Token Index: 646