Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3921 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.8180. Min Act: -0.1700
Data Index: 89554 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.8180. Min Act: -0.1700
Data Index: 1040816 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7861. Min Act: -0.1700
Data Index: 4130983 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.8180. Min Act: -0.1700
Data Index: 4720517 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7861. Min Act: -0.1700
Data Index: 7609707 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7702. Min Act: -0.1700
Data Index: 61386 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7702. Min Act: -0.1700
Data Index: 4129482 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7702. Min Act: -0.1700
Data Index: 7388356 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7702. Min Act: -0.1700
Data Index: 3390491 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7861. Min Act: -0.1700
Data Index: 1065510 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7702. Min Act: -0.1700
Data Index: 2090053 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7702. Min Act: -0.1700
Data Index: 6332391 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7702. Min Act: -0.1700
Data Index: 5953423 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7702. Min Act: -0.1700
Data Index: 5009492 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7702. Min Act: -0.1700
Data Index: 611046 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7543. Min Act: -0.1700
Data Index: 720179 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7702. Min Act: -0.1700
Data Index: 4109496 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7543. Min Act: -0.1700
Data Index: 2493649 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7543. Min Act: -0.1700
Data Index: 2523225 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8180. Min Range: -2.8180
Max Act: 2.7702. Min Act: -0.1700
Data Index: 2653699 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19