Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4763 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3193. Min Range: -8.3193
Max Act: 8.3193. Min Act: -0.1700
Data Index: 7218859 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3193. Min Range: -8.3193
Max Act: 8.3193. Min Act: -0.1700
Data Index: 8222910 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3193. Min Range: -8.3193
Max Act: 8.0693. Min Act: -0.1700
Data Index: 1521889 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3193. Min Range: -8.3193
Max Act: 8.0693. Min Act: -0.1700
Data Index: 3189141 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3193. Min Range: -8.3193
Max Act: 8.0693. Min Act: -0.1700
Data Index: 4140411 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.9443. Min Act: -0.1700
Data Index: 6087688 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.9443. Min Act: -0.1700
Data Index: 2658794 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.9443. Min Act: -0.1700
Data Index: 1517808 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.9443. Min Act: -0.1700
Data Index: 2692062 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.9443. Min Act: -0.1700
Data Index: 6686379 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.8818. Min Act: -0.1700
Data Index: 4441665 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.8818. Min Act: -0.1700
Data Index: 238435 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.8818. Min Act: -0.1700
Data Index: 1988074 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.8193. Min Act: -0.1700
Data Index: 2518988 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.8193. Min Act: -0.1700
Data Index: 5783925 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.8193. Min Act: -0.1700
Data Index: 700541 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.8193. Min Act: -0.1700
Data Index: 6540985 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.8193. Min Act: -0.1700
Data Index: 6296123 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.7568. Min Act: -0.1700
Data Index: 118217 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3193. Min Range: -8.3193
Max Act: 7.7568. Min Act: -0.1700
Data Index: 118121 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19