Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5155 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.7786. Min Act: -0.1700
Data Index: 8496348 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.7474. Min Act: -0.1700
Data Index: 1217838 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.7474. Min Act: -0.1700
Data Index: 6832090 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.7474. Min Act: -0.1700
Data Index: 2354237 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.7161. Min Act: -0.1700
Data Index: 6394656 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.7161. Min Act: -0.1700
Data Index: 8722525 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.7161. Min Act: -0.1700
Data Index: 2039304 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.7161. Min Act: -0.1700
Data Index: 8560855 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.7161. Min Act: -0.1700
Data Index: 6922674 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.6848. Min Act: -0.1700
Data Index: 442670 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.6848. Min Act: -0.1700
Data Index: 3047069 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.6848. Min Act: -0.1700
Data Index: 8379136 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.6848. Min Act: -0.1700
Data Index: 2956226 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.6848. Min Act: -0.1700
Data Index: 3120448 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.6848. Min Act: -0.1700
Data Index: 2947255 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.6848. Min Act: -0.1700
Data Index: 6304598 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.6848. Min Act: -0.1700
Data Index: 2512512 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.6535. Min Act: -0.1700
Data Index: 3652895 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.6535. Min Act: -0.1700
Data Index: 5031334 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7786. Min Range: -3.7786
Max Act: 3.6535. Min Act: -0.1700
Data Index: 2941470 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19