Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 232 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.3668. Min Act: -0.1700
Data Index: 5234313 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.3668. Min Act: -0.1700
Data Index: 8457521 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.3043. Min Act: -0.1700
Data Index: 3827815 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.2418. Min Act: -0.1700
Data Index: 5930073 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.3043. Min Act: -0.1700
Data Index: 7781207 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.2418. Min Act: -0.1700
Data Index: 8121933 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.3043. Min Act: -0.1700
Data Index: 4949061 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.2105. Min Act: -0.1700
Data Index: 4348136 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.2418. Min Act: -0.1700
Data Index: 8540320 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.1793. Min Act: -0.1700
Data Index: 3285399 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.1793. Min Act: -0.1700
Data Index: 4730692 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.1793. Min Act: -0.1700
Data Index: 1689904 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.1793. Min Act: -0.1700
Data Index: 6965462 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.1480. Min Act: -0.1700
Data Index: 6350878 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.1480. Min Act: -0.1700
Data Index: 4801806 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.1168. Min Act: -0.1700
Data Index: 3561379 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.1168. Min Act: -0.1700
Data Index: 3702642 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.1168. Min Act: -0.1700
Data Index: 1654968 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.0855. Min Act: -0.1700
Data Index: 1937535 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3668. Min Range: -5.3668
Max Act: 5.1168. Min Act: -0.1700
Data Index: 2224208 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19