Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3207 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7815. Min Act: -0.1700
Data Index: 2564925 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7815. Min Act: -0.1700
Data Index: 1857128 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7503. Min Act: -0.1700
Data Index: 6053061 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7503. Min Act: -0.1700
Data Index: 6861663 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7346. Min Act: -0.1700
Data Index: 1154554 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7346. Min Act: -0.1700
Data Index: 1679140 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7346. Min Act: -0.1700
Data Index: 7689966 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7190. Min Act: -0.1700
Data Index: 8618061 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7190. Min Act: -0.1700
Data Index: 525394 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7190. Min Act: -0.1700
Data Index: 2456591 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7190. Min Act: -0.1700
Data Index: 5024101 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7190. Min Act: -0.1700
Data Index: 7290276 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7033. Min Act: -0.1700
Data Index: 7710594 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7033. Min Act: -0.1700
Data Index: 3350067 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7033. Min Act: -0.1700
Data Index: 3165068 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7033. Min Act: -0.1700
Data Index: 5672374 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7033. Min Act: -0.1700
Data Index: 7597039 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.7033. Min Act: -0.1700
Data Index: 369747 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.6877. Min Act: -0.1700
Data Index: 7573925 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7815. Min Range: -3.7815
Max Act: 3.6877. Min Act: -0.1700
Data Index: 5885710 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19