Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2911 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0600. Min Range: -7.0600
Max Act: 7.0600. Min Act: -0.1700
Data Index: 5310610 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.9350. Min Act: -0.1700
Data Index: 6364033 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.9350. Min Act: -0.1700
Data Index: 4894897 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.8725. Min Act: -0.1700
Data Index: 1499495 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.7788. Min Act: -0.1700
Data Index: 1532440 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.7788. Min Act: -0.1700
Data Index: 2759587 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.7788. Min Act: -0.1700
Data Index: 7360663 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.7475. Min Act: -0.1700
Data Index: 2016403 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.7788. Min Act: -0.1700
Data Index: 2311234 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.7788. Min Act: -0.1700
Data Index: 3462994 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.6850. Min Act: -0.1700
Data Index: 6438498 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.7163. Min Act: -0.1700
Data Index: 1201102 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.7163. Min Act: -0.1700
Data Index: 542346 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.6850. Min Act: -0.1700
Data Index: 7926866 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.5913. Min Act: -0.1700
Data Index: 790703 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.5913. Min Act: -0.1700
Data Index: 3226808 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.5913. Min Act: -0.1700
Data Index: 6681419 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.5913. Min Act: -0.1700
Data Index: 4720329 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.5600. Min Act: -0.1700
Data Index: 5092998 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0600. Min Range: -7.0600
Max Act: 6.5288. Min Act: -0.1700
Data Index: 1722669 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19