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

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

Neuron 5285 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: 1.0516. Min Range: -1.0516

Max Act: 1.0516. Min Act: -0.0002

Data Index: 801871 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.9504. Min Act: -0.0002

Data Index: 31006 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.9380. Min Act: -0.0002

Data Index: 327370 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.9417. Min Act: -0.0002

Data Index: 708842 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8980. Min Act: -0.0002

Data Index: 1104091 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8742. Min Act: -0.0002

Data Index: 1180790 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8759. Min Act: -0.0002

Data Index: 253809 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8762. Min Act: -0.0003

Data Index: 242950 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8483. Min Act: -0.0002

Data Index: 242826 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8325. Min Act: -0.0003

Data Index: 718916 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8356. Min Act: -0.0002

Data Index: 1174180 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8326. Min Act: -0.0002

Data Index: 783237 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8156. Min Act: -0.0002

Data Index: 441864 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8331. Min Act: -0.0002

Data Index: 1333664 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8125. Min Act: -0.0002

Data Index: 912844 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8006. Min Act: -0.0002

Data Index: 7127 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7996. Min Act: -0.0002

Data Index: 919817 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7996. Min Act: -0.0002

Data Index: 921917 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7914. Min Act: -0.0002

Data Index: 1166499 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7992. Min Act: -0.0002

Data Index: 518696 (C4 (Web Text))

Max Activating Token Index: 90