Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2456 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.6098. Min Act: -0.0000

Data Index: 792908 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4736. Min Act: -0.0000

Data Index: 329695 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5100. Min Act: -0.0000

Data Index: 61938 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4784. Min Act: -0.0000

Data Index: 793594 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4152. Min Act: -0.0000

Data Index: 28499 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4549. Min Act: -0.0000

Data Index: 897244 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4228. Min Act: -0.0000

Data Index: 738350 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4238. Min Act: -0.0000

Data Index: 811261 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4338. Min Act: -0.0000

Data Index: 182521 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4813. Min Act: -0.0000

Data Index: 655359 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1232415 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1107133 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4236. Min Act: -0.0000

Data Index: 278644 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4471. Min Act: -0.0000

Data Index: 309770 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4199. Min Act: -0.0000

Data Index: 108290 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4302. Min Act: -0.0000

Data Index: 447468 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3984. Min Act: -0.0000

Data Index: 557075 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3981. Min Act: -0.0000

Data Index: 214574 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4248. Min Act: -0.0000

Data Index: 753618 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3948. Min Act: -0.0000

Data Index: 881917 (C4 (Web Text))

Max Activating Token Index: 950