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

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

Neuron 3636 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: 0.6891. Min Range: -0.6891

Max Act: 0.6891. Min Act: -0.0000

Data Index: 515212 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1069137 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.6850. Min Act: -0.0000

Data Index: 763285 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1096570 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.6160. Min Act: -0.0000

Data Index: 16847 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.6343. Min Act: -0.0000

Data Index: 463847 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.6261. Min Act: -0.0000

Data Index: 816922 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1388007 (Python Code)

Max Activating Token Index: 316

Text #8

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5526. Min Act: -0.0000

Data Index: 818571 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5502. Min Act: -0.0000

Data Index: 1008483 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1062823 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1645537 (Python Code)

Max Activating Token Index: 727

Text #12

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5021. Min Act: -0.0000

Data Index: 165567 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4686. Min Act: -0.0000

Data Index: 237202 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1047312 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4986. Min Act: -0.0000

Data Index: 1212529 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4993. Min Act: -0.0000

Data Index: 504917 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.5137. Min Act: -0.0000

Data Index: 804074 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1070191 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.6891. Min Range: -0.6891

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1477122 (Python Code)

Max Activating Token Index: 800