Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2572 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.8837. Min Act: -0.1700
Data Index: 7969002 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.8524. Min Act: -0.1700
Data Index: 8077796 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.8524. Min Act: -0.1700
Data Index: 6853251 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.8681. Min Act: -0.1700
Data Index: 8248362 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.8368. Min Act: -0.1700
Data Index: 5886178 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.8055. Min Act: -0.1700
Data Index: 830938 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.8368. Min Act: -0.1700
Data Index: 1486592 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.8055. Min Act: -0.1700
Data Index: 5150336 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.8212. Min Act: -0.1700
Data Index: 4378018 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.7743. Min Act: -0.1700
Data Index: 1786927 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.8212. Min Act: -0.1700
Data Index: 8772421 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.7899. Min Act: -0.1700
Data Index: 178780 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.7586. Min Act: -0.1700
Data Index: 7556585 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.7586. Min Act: -0.1700
Data Index: 8578809 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.7430. Min Act: -0.1700
Data Index: 911012 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.7743. Min Act: -0.1700
Data Index: 4043900 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.7430. Min Act: -0.1700
Data Index: 2841667 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.7430. Min Act: -0.1700
Data Index: 2448762 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.7117. Min Act: -0.1700
Data Index: 6753564 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8837. Min Range: -3.8837
Max Act: 3.7117. Min Act: -0.1700
Data Index: 2421547 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19