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

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

Neuron 3513 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: 2.1039. Min Range: -2.1039

Max Act: 2.1039. Min Act: -0.0002

Data Index: 1109010 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.9895. Min Act: -0.0002

Data Index: 577063 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.9815. Min Act: -0.0002

Data Index: 607381 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.9711. Min Act: -0.0002

Data Index: 888714 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.9085. Min Act: -0.0002

Data Index: 30951 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.9456. Min Act: -0.0002

Data Index: 1176295 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.8590. Min Act: -0.0002

Data Index: 595247 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.9394. Min Act: -0.0002

Data Index: 974080 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.8145. Min Act: -0.0002

Data Index: 522361 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.8149. Min Act: -0.0002

Data Index: 1282303 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.8040. Min Act: -0.0002

Data Index: 955036 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.7819. Min Act: -0.0002

Data Index: 314825 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.7845. Min Act: -0.0002

Data Index: 1261656 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.8297. Min Act: -0.0002

Data Index: 624430 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.8391. Min Act: -0.0002

Data Index: 682842 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.7690. Min Act: -0.0002

Data Index: 594032 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.7920. Min Act: -0.0002

Data Index: 38736 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.8328. Min Act: -0.0002

Data Index: 88679 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.7173. Min Act: -0.0002

Data Index: 995583 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 2.1039. Min Range: -2.1039

Max Act: 1.7410. Min Act: -0.0002

Data Index: 1318985 (C4 (Web Text))

Max Activating Token Index: 385