Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3782 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2718. Min Range: -7.2718
Max Act: 7.2718. Min Act: -0.1700
Data Index: 511920 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2718. Min Range: -7.2718
Max Act: 7.2093. Min Act: -0.1700
Data Index: 6002453 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2718. Min Range: -7.2718
Max Act: 7.0218. Min Act: -0.1700
Data Index: 6389492 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.9593. Min Act: -0.1700
Data Index: 1202516 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.9593. Min Act: -0.1700
Data Index: 4532521 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.9593. Min Act: -0.1700
Data Index: 2328276 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.8968. Min Act: -0.1700
Data Index: 7191790 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.8968. Min Act: -0.1700
Data Index: 1724000 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.8656. Min Act: -0.1700
Data Index: 1555412 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.8656. Min Act: -0.1700
Data Index: 3541100 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.8656. Min Act: -0.1700
Data Index: 6795473 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.8656. Min Act: -0.1700
Data Index: 1032142 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.8343. Min Act: -0.1700
Data Index: 6965797 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.8656. Min Act: -0.1700
Data Index: 1775563 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.8343. Min Act: -0.1700
Data Index: 4989973 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.8343. Min Act: -0.1697
Data Index: 6858803 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.8343. Min Act: -0.1700
Data Index: 3524465 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.8031. Min Act: -0.1700
Data Index: 4300444 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.8031. Min Act: -0.1700
Data Index: 4114665 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2718. Min Range: -7.2718
Max Act: 6.8031. Min Act: -0.1699
Data Index: 900926 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19