Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1584 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.7127. Min Act: -0.1700
Data Index: 488899 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 1796093 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 3773035 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 4499884 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 4067107 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 4831231 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 3339524 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 750467 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 316301 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 3238337 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 3673844 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 863165 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 975396 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 3851752 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 1604048 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 3322339 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 3207125 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 3882627 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1698
Data Index: 952735 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7127. Min Range: -2.7127
Max Act: 2.6967. Min Act: -0.1700
Data Index: 2055652 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19