Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3778 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1576. Min Range: -9.1576
Max Act: 9.1576. Min Act: -0.1700
Data Index: 7426665 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.9076. Min Act: -0.1700
Data Index: 6592518 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.7826. Min Act: -0.1700
Data Index: 7696576 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.6576. Min Act: -0.1700
Data Index: 1991330 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.5326. Min Act: -0.1700
Data Index: 5692251 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.4076. Min Act: -0.1700
Data Index: 1629748 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.2826. Min Act: -0.1700
Data Index: 619157 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.1576. Min Act: -0.1700
Data Index: 609988 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.0951. Min Act: -0.1700
Data Index: 7251511 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.0951. Min Act: -0.1700
Data Index: 1922652 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.0951. Min Act: -0.1700
Data Index: 3344523 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.0326. Min Act: -0.1700
Data Index: 7087697 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.0326. Min Act: -0.1700
Data Index: 6842799 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.0326. Min Act: -0.1700
Data Index: 8184680 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.0326. Min Act: -0.1700
Data Index: 8251718 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.0326. Min Act: -0.1700
Data Index: 18437 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.0326. Min Act: -0.1700
Data Index: 1041825 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1576. Min Range: -9.1576
Max Act: 7.9701. Min Act: -0.1700
Data Index: 2761280 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1576. Min Range: -9.1576
Max Act: 7.9701. Min Act: -0.1700
Data Index: 6231710 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1576. Min Range: -9.1576
Max Act: 8.0326. Min Act: -0.1700
Data Index: 6388840 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19