Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 768 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.0804. Min Range: -2.0804
Max Act: 2.0804. Min Act: 0.0000
Data Index: 1088768 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.7633. Min Act: 0.0000
Data Index: 573963 (The Pile)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.8482. Min Act: -0.0000
Data Index: 258044 (The Pile)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.6142. Min Act: -0.0001
Data Index: 1553691 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.5232. Min Act: -0.0000
Data Index: 1775107 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.4192. Min Act: -0.0000
Data Index: 176113 (The Pile)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.6193. Min Act: -0.0001
Data Index: 1735311 (The Pile)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.4543. Min Act: -0.0000
Data Index: 139632 (The Pile)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.4990. Min Act: -0.0000
Data Index: 1113595 (The Pile)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.5821. Min Act: -0.0000
Data Index: 1058773 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.3069. Min Act: -0.0001
Data Index: 109697 (The Pile)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.4012. Min Act: -0.0001
Data Index: 967928 (The Pile)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.5429. Min Act: 0.0000
Data Index: 1103021 (The Pile)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.2654. Min Act: -0.0001
Data Index: 769441 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.3195. Min Act: -0.0000
Data Index: 1698310 (The Pile)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.5069. Min Act: -0.0001
Data Index: 991114 (The Pile)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.5055. Min Act: -0.0001
Data Index: 809896 (The Pile)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.3743. Min Act: -0.0000
Data Index: 1800172 (The Pile)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.3299. Min Act: -0.0000
Data Index: 305220 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0804. Min Range: -2.0804
Max Act: 1.3516. Min Act: -0.0000
Data Index: 999448 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19