Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3119 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.7739. Min Range: -2.7739
Max Act: 2.7739. Min Act: -0.0000
Data Index: 102106 (The Pile)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7739. Min Range: -2.7739
Max Act: 2.4947. Min Act: -0.0000
Data Index: 135889 (The Pile)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7739. Min Range: -2.7739
Max Act: 2.4578. Min Act: -0.0000
Data Index: 738863 (The Pile)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7739. Min Range: -2.7739
Max Act: 2.3127. Min Act: -0.0000
Data Index: 1748656 (The Pile)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7739. Min Range: -2.7739
Max Act: 2.2581. Min Act: -0.0000
Data Index: 1215957 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7739. Min Range: -2.7739
Max Act: 2.3297. Min Act: -0.0000
Data Index: 1163846 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7739. Min Range: -2.7739
Max Act: 2.3082. Min Act: -0.0000
Data Index: 522421 (The Pile)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7739. Min Range: -2.7739
Max Act: 2.2293. Min Act: -0.0000
Data Index: 249495 (The Pile)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7739. Min Range: -2.7739
Max Act: 1.9974. Min Act: -0.0000
Data Index: 1075172 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7739. Min Range: -2.7739
Max Act: 2.1097. Min Act: -0.0000
Data Index: 1986191 (The Pile)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7739. Min Range: -2.7739
Max Act: 1.9834. Min Act: -0.0000
Data Index: 33444 (The Pile)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7739. Min Range: -2.7739
Max Act: 1.9464. Min Act: -0.0000
Data Index: 363070 (The Pile)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7739. Min Range: -2.7739
Max Act: 1.9871. Min Act: -0.0000
Data Index: 1858964 (The Pile)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7739. Min Range: -2.7739
Max Act: 2.0568. Min Act: -0.0000
Data Index: 444928 (The Pile)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7739. Min Range: -2.7739
Max Act: 2.0614. Min Act: -0.0000
Data Index: 1216241 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7739. Min Range: -2.7739
Max Act: 1.6526. Min Act: -0.0000
Data Index: 1321256 (The Pile)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7739. Min Range: -2.7739
Max Act: 2.0414. Min Act: -0.0000
Data Index: 957218 (The Pile)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7739. Min Range: -2.7739
Max Act: 1.8369. Min Act: -0.0000
Data Index: 662866 (The Pile)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7739. Min Range: -2.7739
Max Act: 1.7125. Min Act: -0.0000
Data Index: 200853 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7739. Min Range: -2.7739
Max Act: 1.7858. Min Act: -0.0000
Data Index: 977674 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19