Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5742 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0285. Min Range: -4.0285
Max Act: 4.0285. Min Act: -0.1700
Data Index: 2216871 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0285. Min Range: -4.0285
Max Act: 4.0285. Min Act: -0.1700
Data Index: 1091235 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0285. Min Range: -4.0285
Max Act: 4.0285. Min Act: -0.1700
Data Index: 5566214 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9973. Min Act: -0.1700
Data Index: 1821931 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9973. Min Act: -0.1700
Data Index: 6554974 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9973. Min Act: -0.1700
Data Index: 8770055 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9973. Min Act: -0.1700
Data Index: 1021865 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9973. Min Act: -0.1700
Data Index: 4085297 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9660. Min Act: -0.1700
Data Index: 632585 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9660. Min Act: -0.1700
Data Index: 7484299 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9660. Min Act: -0.1700
Data Index: 5749597 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9660. Min Act: -0.1700
Data Index: 2900967 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9660. Min Act: -0.1700
Data Index: 373186 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9660. Min Act: -0.1700
Data Index: 5356254 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9660. Min Act: -0.1700
Data Index: 7974681 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9660. Min Act: -0.1700
Data Index: 2162051 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9660. Min Act: -0.1700
Data Index: 7878926 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9347. Min Act: -0.1700
Data Index: 1484584 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9347. Min Act: -0.1700
Data Index: 3971093 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9347. Min Act: -0.1700
Data Index: 7502252 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19