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

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

Neuron 767 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.8160. Min Act: -0.0002

Data Index: 856790 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.4743. Min Act: -0.0002

Data Index: 1157999 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.4414. Min Act: -0.0002

Data Index: 811101 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.4554. Min Act: -0.0002

Data Index: 1087260 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.3921. Min Act: -0.0002

Data Index: 191955 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.3894. Min Act: -0.0002

Data Index: 407107 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.3013. Min Act: -0.0002

Data Index: 1242017 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.3184. Min Act: -0.0002

Data Index: 446400 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.3051. Min Act: -0.0002

Data Index: 343110 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.2649. Min Act: -0.0002

Data Index: 144047 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.2907. Min Act: -0.0002

Data Index: 691808 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.2813. Min Act: -0.0002

Data Index: 209732 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.2249. Min Act: -0.0002

Data Index: 1132637 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.1983. Min Act: -0.0002

Data Index: 967358 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.1971. Min Act: -0.0002

Data Index: 256638 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.1710. Min Act: -0.0002

Data Index: 776077 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.0641. Min Act: -0.0002

Data Index: 798021 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.0430. Min Act: -0.0002

Data Index: 1028100 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.0187. Min Act: -0.0002

Data Index: 307396 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 2.8160. Min Range: -2.8160

Max Act: 2.0482. Min Act: -0.0002

Data Index: 91726 (C4 (Web Text))

Max Activating Token Index: 634