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

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

Neuron 155 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: 0.4554. Min Range: -0.4554

Max Act: 0.4554. Min Act: -0.0000

Data Index: 658341 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1050212 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.4317. Min Act: -0.0000

Data Index: 337323 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3830. Min Act: -0.0000

Data Index: 684624 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3861. Min Act: -0.0000

Data Index: 78043 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3819. Min Act: -0.0000

Data Index: 726159 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1052751 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3680. Min Act: -0.0000

Data Index: 395796 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3660. Min Act: -0.0000

Data Index: 6835 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3627. Min Act: -0.0000

Data Index: 139592 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3408. Min Act: -0.0000

Data Index: 278951 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1134922 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1344136 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1249645 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1068857 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3180. Min Act: -0.0000

Data Index: 866888 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3218. Min Act: -0.0000

Data Index: 285791 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1126710 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3195. Min Act: -0.0000

Data Index: 128876 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.4554. Min Range: -0.4554

Max Act: 0.3194. Min Act: -0.0000

Data Index: 709332 (C4 (Web Text))

Max Activating Token Index: 96