Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5261 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3882. Min Act: -0.1700
Data Index: 1006010 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3882. Min Act: -0.1700
Data Index: 5290166 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3882. Min Act: -0.1700
Data Index: 4423612 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3570. Min Act: -0.1700
Data Index: 3674511 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3570. Min Act: -0.1700
Data Index: 5365741 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3570. Min Act: -0.1700
Data Index: 900111 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3570. Min Act: -0.1700
Data Index: 401438 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3257. Min Act: -0.1700
Data Index: 6963447 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3570. Min Act: -0.1700
Data Index: 5214749 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3257. Min Act: -0.1700
Data Index: 2027279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3257. Min Act: -0.1700
Data Index: 6850702 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3257. Min Act: -0.1700
Data Index: 421638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3257. Min Act: -0.1700
Data Index: 2213631 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3257. Min Act: -0.1700
Data Index: 5042407 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3257. Min Act: -0.1700
Data Index: 4758170 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3257. Min Act: -0.1700
Data Index: 776659 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3257. Min Act: -0.1700
Data Index: 626709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3257. Min Act: -0.1700
Data Index: 4419452 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3257. Min Act: -0.1700
Data Index: 3771489 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3882. Min Range: -5.3882
Max Act: 5.3257. Min Act: -0.1700
Data Index: 1282597 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19