Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4080 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.2056. Min Act: -0.1700
Data Index: 5998253 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.1743. Min Act: -0.1700
Data Index: 7147483 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.1743. Min Act: -0.1700
Data Index: 5658574 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.1743. Min Act: -0.1700
Data Index: 8709361 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.1118. Min Act: -0.1700
Data Index: 4656275 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.1431. Min Act: -0.1700
Data Index: 2064254 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.1118. Min Act: -0.1700
Data Index: 1059143 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.0806. Min Act: -0.1700
Data Index: 7075221 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.0806. Min Act: -0.1700
Data Index: 1767295 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.0806. Min Act: -0.1700
Data Index: 3740605 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.0181. Min Act: -0.1700
Data Index: 3181979 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.0493. Min Act: -0.1700
Data Index: 4638775 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.0493. Min Act: -0.1700
Data Index: 462112 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.0493. Min Act: -0.1700
Data Index: 5237540 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.0493. Min Act: -0.1700
Data Index: 2590990 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.0181. Min Act: -0.1700
Data Index: 2635314 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.0181. Min Act: -0.1700
Data Index: 6809226 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.0181. Min Act: -0.1700
Data Index: 1731118 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.0181. Min Act: -0.1700
Data Index: 6222884 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2056. Min Range: -5.2056
Max Act: 5.0181. Min Act: -0.1700
Data Index: 1159043 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19