Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2987 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.6062. Min Act: -0.0000
Data Index: 517 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.5486. Min Act: -0.0000
Data Index: 158553 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.5485. Min Act: -0.0000
Data Index: 378532 (The Pile)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.5687. Min Act: -0.0000
Data Index: 216413 (The Pile)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.4633. Min Act: -0.0000
Data Index: 322606 (The Pile)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.3869. Min Act: -0.0000
Data Index: 1507185 (The Pile)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.4581. Min Act: -0.0000
Data Index: 421183 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.4483. Min Act: -0.0000
Data Index: 840881 (The Pile)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.5253. Min Act: -0.0000
Data Index: 596964 (The Pile)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.4413. Min Act: -0.0000
Data Index: 1811058 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.4094. Min Act: -0.0000
Data Index: 623091 (The Pile)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.4263. Min Act: -0.0000
Data Index: 1273875 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.4105. Min Act: -0.0000
Data Index: 995236 (The Pile)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.4150. Min Act: -0.0000
Data Index: 669865 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.4087. Min Act: -0.0000
Data Index: 112672 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.3153. Min Act: -0.0000
Data Index: 1175959 (The Pile)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.5631. Min Act: -0.0000
Data Index: 385877 (The Pile)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.3766. Min Act: -0.0000
Data Index: 657083 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.2907. Min Act: -0.0000
Data Index: 47120 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6062. Min Range: -1.6062
Max Act: 1.3642. Min Act: -0.0000
Data Index: 622196 (The Pile)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19