Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1035 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2113. Min Range: -5.2113
Max Act: 5.2113. Min Act: -0.1700
Data Index: 2135009 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2113. Min Range: -5.2113
Max Act: 5.1801. Min Act: -0.1700
Data Index: 5823121 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2113. Min Range: -5.2113
Max Act: 5.1176. Min Act: -0.1700
Data Index: 2135004 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2113. Min Range: -5.2113
Max Act: 5.0551. Min Act: -0.1700
Data Index: 8040703 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2113. Min Range: -5.2113
Max Act: 5.0238. Min Act: -0.1700
Data Index: 4707939 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.7426. Min Act: -0.1700
Data Index: 8014524 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.7113. Min Act: -0.1700
Data Index: 2660149 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.7113. Min Act: -0.1700
Data Index: 7454265 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.7113. Min Act: -0.1700
Data Index: 3739774 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.6801. Min Act: -0.1700
Data Index: 6494192 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.6801. Min Act: -0.1700
Data Index: 6952387 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.6488. Min Act: -0.1700
Data Index: 7256077 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.6488. Min Act: -0.1700
Data Index: 513028 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.6176. Min Act: -0.1700
Data Index: 4751011 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.6176. Min Act: -0.1700
Data Index: 4752014 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.6176. Min Act: -0.1700
Data Index: 1528548 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.6488. Min Act: -0.1700
Data Index: 5948746 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.6176. Min Act: -0.1700
Data Index: 3438941 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.6176. Min Act: -0.1700
Data Index: 2941239 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2113. Min Range: -5.2113
Max Act: 4.5238. Min Act: -0.1700
Data Index: 2983233 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19