Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 4050 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.1135. Min Act: -0.0001
Data Index: 1905204 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.1015. Min Act: -0.0001
Data Index: 1190349 (The Pile)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0906. Min Act: -0.0001
Data Index: 719758 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0869. Min Act: -0.0001
Data Index: 765752 (The Pile)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0898. Min Act: -0.0001
Data Index: 595407 (The Pile)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0795. Min Act: -0.0001
Data Index: 1571944 (The Pile)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0789. Min Act: -0.0001
Data Index: 1689580 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0844. Min Act: -0.0001
Data Index: 1840917 (The Pile)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0811. Min Act: -0.0001
Data Index: 1142618 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0792. Min Act: -0.0001
Data Index: 1972203 (The Pile)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0766. Min Act: -0.0001
Data Index: 1894224 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0813. Min Act: -0.0001
Data Index: 370193 (The Pile)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0800. Min Act: -0.0001
Data Index: 137288 (The Pile)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0814. Min Act: -0.0001
Data Index: 1307016 (The Pile)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0771. Min Act: -0.0001
Data Index: 891191 (The Pile)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0841. Min Act: -0.0001
Data Index: 564575 (The Pile)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0747. Min Act: -0.0001
Data Index: 1136486 (The Pile)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0753. Min Act: -0.0001
Data Index: 70143 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0713. Min Act: -0.0001
Data Index: 931799 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1135. Min Range: -0.1135
Max Act: 0.0743. Min Act: -0.0001
Data Index: 1693401 (The Pile)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19