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

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

Neuron 687 in Layer 0

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: 0.7388. Min Range: -0.7388

Max Act: 0.7388. Min Act: -0.0001

Data Index: 230893 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.7364. Min Act: -0.0001

Data Index: 63819 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.7022. Min Act: -0.0001

Data Index: 643510 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6794. Min Act: -0.0001

Data Index: 374615 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6898. Min Act: -0.0001

Data Index: 361366 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6736. Min Act: -0.0001

Data Index: 902894 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6669. Min Act: -0.0001

Data Index: 608191 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6637. Min Act: -0.0001

Data Index: 1345851 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6694. Min Act: -0.0002

Data Index: 818700 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6702. Min Act: -0.0001

Data Index: 1192309 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6578. Min Act: -0.0001

Data Index: 778029 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6522. Min Act: -0.0001

Data Index: 1216319 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6476. Min Act: -0.0001

Data Index: 536882 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6525. Min Act: -0.0001

Data Index: 875827 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6413. Min Act: -0.0001

Data Index: 1102750 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6413. Min Act: -0.0001

Data Index: 1077985 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6414. Min Act: -0.0001

Data Index: 382676 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6399. Min Act: -0.0001

Data Index: 549055 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6501. Min Act: -0.0001

Data Index: 151815 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6516. Min Act: -0.0001

Data Index: 79145 (C4 (Web Text))

Max Activating Token Index: 1023