Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2594 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1560. Min Range: -6.1560
Max Act: 6.1560. Min Act: -0.1700
Data Index: 3787813 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.9373. Min Act: -0.1700
Data Index: 2634066 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8748. Min Act: -0.1700
Data Index: 3403079 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8748. Min Act: -0.1700
Data Index: 1767882 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8748. Min Act: -0.1700
Data Index: 8501314 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8748. Min Act: -0.1700
Data Index: 2192612 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8123. Min Act: -0.1700
Data Index: 1433127 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8435. Min Act: -0.1700
Data Index: 6560618 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8123. Min Act: -0.1700
Data Index: 3255615 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8123. Min Act: -0.1700
Data Index: 2076199 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8123. Min Act: -0.1700
Data Index: 957721 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8123. Min Act: -0.1700
Data Index: 8459828 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8123. Min Act: -0.1700
Data Index: 7875011 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8123. Min Act: -0.1700
Data Index: 7728443 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8123. Min Act: -0.1700
Data Index: 5989535 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8123. Min Act: -0.1700
Data Index: 1262500 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.8123. Min Act: -0.1700
Data Index: 5866106 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.7810. Min Act: -0.1700
Data Index: 3392752 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.7810. Min Act: -0.1700
Data Index: 312704 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1560. Min Range: -6.1560
Max Act: 5.7498. Min Act: -0.1700
Data Index: 3594501 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19