Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3260 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4856. Min Range: -6.4856
Max Act: 6.4856. Min Act: -0.1700
Data Index: 4740550 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4856. Min Range: -6.4856
Max Act: 6.0168. Min Act: -0.1700
Data Index: 7573993 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.8606. Min Act: -0.1700
Data Index: 7055283 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.7043. Min Act: -0.1700
Data Index: 2822158 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.7356. Min Act: -0.1700
Data Index: 8658470 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.7356. Min Act: -0.1700
Data Index: 4676791 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.6731. Min Act: -0.1700
Data Index: 7907652 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.6418. Min Act: -0.1700
Data Index: 6332414 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.6731. Min Act: -0.1700
Data Index: 6576752 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.6106. Min Act: -0.1700
Data Index: 2560987 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.6418. Min Act: -0.1700
Data Index: 829237 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.6418. Min Act: -0.1700
Data Index: 5259868 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.6106. Min Act: -0.1700
Data Index: 6658831 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.6418. Min Act: -0.1700
Data Index: 3530082 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.6106. Min Act: -0.1700
Data Index: 2357479 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.6106. Min Act: -0.1700
Data Index: 2448215 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.6106. Min Act: -0.1700
Data Index: 5985226 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.5793. Min Act: -0.1700
Data Index: 3992313 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.5793. Min Act: -0.1700
Data Index: 1468033 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4856. Min Range: -6.4856
Max Act: 5.5793. Min Act: -0.1700
Data Index: 802471 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19