Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1011 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1041. Min Range: -7.1041
Max Act: 7.1041. Min Act: -0.1700
Data Index: 6067204 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.8541. Min Act: -0.1700
Data Index: 4003619 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.6979. Min Act: -0.1700
Data Index: 4512905 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.6979. Min Act: -0.1700
Data Index: 7574606 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.6979. Min Act: -0.1700
Data Index: 7528 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.5729. Min Act: -0.1700
Data Index: 795082 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.5729. Min Act: -0.1700
Data Index: 3205414 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.5729. Min Act: -0.1700
Data Index: 7766493 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.5416. Min Act: -0.1700
Data Index: 1238123 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.5416. Min Act: -0.1700
Data Index: 7529700 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.5416. Min Act: -0.1700
Data Index: 842482 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.5104. Min Act: -0.1700
Data Index: 633693 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.5416. Min Act: -0.1700
Data Index: 6403547 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.5104. Min Act: -0.1700
Data Index: 8680297 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.4791. Min Act: -0.1700
Data Index: 1192952 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.4791. Min Act: -0.1700
Data Index: 4837696 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.5104. Min Act: -0.1700
Data Index: 5590241 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.5104. Min Act: -0.1700
Data Index: 11026 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.4166. Min Act: -0.1700
Data Index: 216751 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1041. Min Range: -7.1041
Max Act: 6.4479. Min Act: -0.1700
Data Index: 5730761 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19