Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1532 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4161. Min Range: -7.4161
Max Act: 7.4161. Min Act: -0.1700
Data Index: 665693 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4161. Min Range: -7.4161
Max Act: 7.1036. Min Act: -0.1700
Data Index: 5042062 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4161. Min Range: -7.4161
Max Act: 7.0724. Min Act: -0.1700
Data Index: 5746321 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.7911. Min Act: -0.1700
Data Index: 6311411 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.8224. Min Act: -0.1700
Data Index: 8034383 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.7911. Min Act: -0.1700
Data Index: 3341931 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.6974. Min Act: -0.1700
Data Index: 8562234 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.6349. Min Act: -0.1700
Data Index: 2590109 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.5724. Min Act: -0.1700
Data Index: 4471696 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.5724. Min Act: -0.1700
Data Index: 972423 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.4161. Min Act: -0.1700
Data Index: 563886 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.4786. Min Act: -0.1700
Data Index: 3122784 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.3849. Min Act: -0.1700
Data Index: 6216020 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.2911. Min Act: -0.1700
Data Index: 5529800 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.3224. Min Act: -0.1700
Data Index: 229255 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.2911. Min Act: -0.1700
Data Index: 672907 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.3224. Min Act: -0.1700
Data Index: 5709178 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.2911. Min Act: -0.1700
Data Index: 5563201 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.2911. Min Act: -0.1700
Data Index: 2999768 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4161. Min Range: -7.4161
Max Act: 6.2599. Min Act: -0.1700
Data Index: 5679493 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19