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

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

Neuron 3580 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: 0.8390. Min Range: -0.8390

Max Act: 0.8390. Min Act: -0.0000

Data Index: 666936 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.7983. Min Act: -0.0000

Data Index: 649076 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.7313. Min Act: -0.0000

Data Index: 67758 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1182479 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.7124. Min Act: -0.0000

Data Index: 784829 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.7041. Min Act: -0.0000

Data Index: 990174 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.7287. Min Act: -0.0000

Data Index: 263658 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1169552 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6840. Min Act: -0.0001

Data Index: 1091347 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6897. Min Act: -0.0001

Data Index: 567820 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6464. Min Act: -0.0000

Data Index: 610515 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1181495 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6480. Min Act: -0.0001

Data Index: 542718 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6931. Min Act: -0.0000

Data Index: 1119509 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6464. Min Act: -0.0001

Data Index: 1288863 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6790. Min Act: -0.0000

Data Index: 207878 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6430. Min Act: -0.0000

Data Index: 96095 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6793. Min Act: -0.0000

Data Index: 498361 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6139. Min Act: -0.0000

Data Index: 1196091 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.8390. Min Range: -0.8390

Max Act: 0.6717. Min Act: -0.0000

Data Index: 44861 (C4 (Web Text))

Max Activating Token Index: 936