Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8418. Min Range: -10.8418
Max Act: 10.8418. Min Act: -0.1700
Data Index: 6999656 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8418. Min Range: -10.8418
Max Act: 10.0918. Min Act: -0.1700
Data Index: 1527767 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8418. Min Range: -10.8418
Max Act: 10.0918. Min Act: -0.1700
Data Index: 4338004 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8418. Min Range: -10.8418
Max Act: 10.0918. Min Act: -0.1700
Data Index: 6671454 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8418. Min Range: -10.8418
Max Act: 10.0293. Min Act: -0.1700
Data Index: 2928740 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.9668. Min Act: -0.1700
Data Index: 1275815 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.9043. Min Act: -0.1700
Data Index: 5905815 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.8418. Min Act: -0.1700
Data Index: 2333490 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.7793. Min Act: -0.1700
Data Index: 6089066 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.7168. Min Act: -0.1700
Data Index: 2905123 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.7793. Min Act: -0.1700
Data Index: 3907473 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.7793. Min Act: -0.1700
Data Index: 4156014 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.6543. Min Act: -0.1700
Data Index: 6561873 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.6543. Min Act: -0.1700
Data Index: 6216513 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.6543. Min Act: -0.1700
Data Index: 3129901 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.6543. Min Act: -0.1700
Data Index: 1079879 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.6543. Min Act: -0.1700
Data Index: 543176 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.5918. Min Act: -0.1700
Data Index: 4846734 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.5918. Min Act: -0.1700
Data Index: 3077272 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8418. Min Range: -10.8418
Max Act: 9.5918. Min Act: -0.1700
Data Index: 3757132 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19