Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 508 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.8783. Min Act: -0.1700
Data Index: 13485 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.9096. Min Act: -0.1700
Data Index: 7088951 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.7532. Min Act: -0.1700
Data Index: 7702857 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.7376. Min Act: -0.1700
Data Index: 4104081 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.5967. Min Act: -0.1700
Data Index: 369371 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.5185. Min Act: -0.1700
Data Index: 5875370 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.4715. Min Act: -0.1700
Data Index: 6059862 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.4715. Min Act: -0.1700
Data Index: 7416171 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.5028. Min Act: -0.1700
Data Index: 5693556 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.4715. Min Act: -0.1700
Data Index: 3067016 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.4558. Min Act: -0.1700
Data Index: 5505712 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.4401. Min Act: -0.1700
Data Index: 2138942 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.4088. Min Act: -0.1700
Data Index: 2067087 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.3774. Min Act: -0.1700
Data Index: 1553075 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.3931. Min Act: -0.1700
Data Index: 2726906 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.3931. Min Act: -0.1700
Data Index: 5235979 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.3931. Min Act: -0.1700
Data Index: 5589847 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.3931. Min Act: -0.1700
Data Index: 2423037 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.3774. Min Act: -0.1700
Data Index: 5817318 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9096. Min Range: -3.9096
Max Act: 3.3774. Min Act: -0.1700
Data Index: 7815664 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19