Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1054 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.1933. Min Act: -0.1700
Data Index: 4851732 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.0996. Min Act: -0.1700
Data Index: 8793934 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.0996. Min Act: -0.1700
Data Index: 2952194 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.0371. Min Act: -0.1700
Data Index: 6768067 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.0058. Min Act: -0.1700
Data Index: 2611997 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.0371. Min Act: -0.1700
Data Index: 2062495 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.9433. Min Act: -0.1700
Data Index: 4755652 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.9433. Min Act: -0.1700
Data Index: 806561 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.9120. Min Act: -0.1700
Data Index: 7699365 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.8808. Min Act: -0.1700
Data Index: 5793502 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.8495. Min Act: -0.1700
Data Index: 4552411 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.8495. Min Act: -0.1700
Data Index: 1278066 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.8495. Min Act: -0.1700
Data Index: 1962768 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.8495. Min Act: -0.1700
Data Index: 6439255 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.8495. Min Act: -0.1700
Data Index: 4491934 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.8182. Min Act: -0.1700
Data Index: 4034739 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.8495. Min Act: -0.1700
Data Index: 219336 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.7869. Min Act: -0.1700
Data Index: 6058159 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.8808. Min Act: -0.1700
Data Index: 1782133 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.8495. Min Act: -0.1700
Data Index: 2691052 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19