Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3695 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.9265. Min Act: -0.1700
Data Index: 8615900 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.7390. Min Act: -0.1700
Data Index: 4534949 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.7390. Min Act: -0.1700
Data Index: 4619727 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.7077. Min Act: -0.1700
Data Index: 1080381 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.6140. Min Act: -0.1700
Data Index: 3028701 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.6140. Min Act: -0.1700
Data Index: 7124802 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.4890. Min Act: -0.1700
Data Index: 4136551 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.4577. Min Act: -0.1700
Data Index: 3889655 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.4577. Min Act: -0.1700
Data Index: 7804561 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.4890. Min Act: -0.1700
Data Index: 6636412 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.4265. Min Act: -0.1700
Data Index: 8621425 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.3327. Min Act: -0.1700
Data Index: 7142086 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.3640. Min Act: -0.1700
Data Index: 366488 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.3327. Min Act: -0.1700
Data Index: 5806377 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.3015. Min Act: -0.1700
Data Index: 835539 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.3015. Min Act: -0.1700
Data Index: 6276641 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.2702. Min Act: -0.1700
Data Index: 7097525 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.2702. Min Act: -0.1700
Data Index: 2327634 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.2702. Min Act: -0.1700
Data Index: 7710584 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9265. Min Range: -7.9265
Max Act: 7.2077. Min Act: -0.1700
Data Index: 5271472 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19