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

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

Neuron 5975 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: 0.0496. Min Range: -0.0496

Max Act: 0.0492. Min Act: -0.0002

Data Index: 73300 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0496. Min Act: -0.0002

Data Index: 143548 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0442. Min Act: -0.0002

Data Index: 820701 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0385. Min Act: -0.0002

Data Index: 718777 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0242. Min Act: -0.0002

Data Index: 816418 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1133350 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0231. Min Act: -0.0002

Data Index: 767303 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1000875 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1243722 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0198. Min Act: -0.0002

Data Index: 488904 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0199. Min Act: -0.0002

Data Index: 159878 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0197. Min Act: -0.0002

Data Index: 685805 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0189. Min Act: -0.0002

Data Index: 113337 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0186. Min Act: -0.0002

Data Index: 482492 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0178. Min Act: -0.0002

Data Index: 99211 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0171. Min Act: -0.0002

Data Index: 99238 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0169. Min Act: -0.0002

Data Index: 490190 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0168. Min Act: -0.0002

Data Index: 741200 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0171. Min Act: -0.0002

Data Index: 386646 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0161. Min Act: -0.0002

Data Index: 774530 (C4 (Web Text))

Max Activating Token Index: 773