Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1289 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.5484. Min Act: -0.0000

Data Index: 972383 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.3852. Min Act: -0.0000

Data Index: 49728 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.3781. Min Act: -0.0000

Data Index: 748021 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.3797. Min Act: -0.0000

Data Index: 1089007 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.2545. Min Act: -0.0000

Data Index: 67715 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.2320. Min Act: -0.0000

Data Index: 860462 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.2099. Min Act: -0.0000

Data Index: 571153 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1020136 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.1028. Min Act: -0.0000

Data Index: 104949 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.0562. Min Act: -0.0000

Data Index: 891350 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.0382. Min Act: -0.0000

Data Index: 550616 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 1.5484. Min Range: -1.5484

Max Act: 0.9609. Min Act: -0.0000

Data Index: 98343 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 1.5484. Min Range: -1.5484

Max Act: 1.0094. Min Act: -0.0000

Data Index: 710002 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 1.5484. Min Range: -1.5484

Max Act: 0.9018. Min Act: -0.0000

Data Index: 994814 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 1.5484. Min Range: -1.5484

Max Act: 0.9360. Min Act: -0.0001

Data Index: 820476 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 1.5484. Min Range: -1.5484

Max Act: 0.8850. Min Act: -0.0001

Data Index: 890113 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 1.5484. Min Range: -1.5484

Max Act: 0.8649. Min Act: -0.0000

Data Index: 249834 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 1.5484. Min Range: -1.5484

Max Act: 0.8708. Min Act: -0.0000

Data Index: 420667 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 1.5484. Min Range: -1.5484

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1078332 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 1.5484. Min Range: -1.5484

Max Act: 0.9492. Min Act: -0.0000

Data Index: 673164 (C4 (Web Text))

Max Activating Token Index: 49