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

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

Neuron 5013 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: 1.3937. Min Range: -1.3937

Max Act: 1.3937. Min Act: -0.0000

Data Index: 142190 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1249596 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.7414. Min Act: -0.0000

Data Index: 376207 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1068291 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.6909. Min Act: -0.0000

Data Index: 670892 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.6874. Min Act: -0.0000

Data Index: 18900 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.7379. Min Act: -0.0000

Data Index: 1196061 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.6946. Min Act: -0.0000

Data Index: 951925 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1204881 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.6534. Min Act: -0.0000

Data Index: 355532 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.6381. Min Act: -0.0000

Data Index: 269895 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.6538. Min Act: -0.0000

Data Index: 241361 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.5948. Min Act: -0.0000

Data Index: 157499 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.6221. Min Act: -0.0000

Data Index: 724245 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.6194. Min Act: -0.0000

Data Index: 278266 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.5991. Min Act: -0.0000

Data Index: 88386 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.6170. Min Act: -0.0000

Data Index: 555938 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1172386 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1160590 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.5857. Min Act: -0.0000

Data Index: 409831 (C4 (Web Text))

Max Activating Token Index: 13