Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.6314. Min Act: -0.1700
Data Index: 6061909 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.5689. Min Act: -0.1700
Data Index: 6224549 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.4439. Min Act: -0.1700
Data Index: 6635770 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.4127. Min Act: -0.1700
Data Index: 3964824 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.3814. Min Act: -0.1700
Data Index: 1146270 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.3814. Min Act: -0.1700
Data Index: 1805725 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.3814. Min Act: -0.1700
Data Index: 1805720 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.3502. Min Act: -0.1700
Data Index: 5368142 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.3189. Min Act: -0.1700
Data Index: 2676191 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.2877. Min Act: -0.1700
Data Index: 3015459 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.2564. Min Act: -0.1700
Data Index: 3992032 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.2252. Min Act: -0.1700
Data Index: 3888019 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.2252. Min Act: -0.1700
Data Index: 7875932 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.1939. Min Act: -0.1700
Data Index: 6145793 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.1939. Min Act: -0.1700
Data Index: 2837756 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.2252. Min Act: -0.1700
Data Index: 3294867 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.1939. Min Act: -0.1700
Data Index: 5293089 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.1627. Min Act: -0.1700
Data Index: 8002648 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.1939. Min Act: -0.1700
Data Index: 6837342 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6314. Min Range: -4.6314
Max Act: 4.1939. Min Act: -0.1700
Data Index: 827892 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19