Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2622 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2741. Min Range: -5.2741
Max Act: 5.2741. Min Act: -0.1700
Data Index: 1374889 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2741. Min Range: -5.2741
Max Act: 5.0866. Min Act: -0.1700
Data Index: 4967567 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.9929. Min Act: -0.1700
Data Index: 8306681 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.9929. Min Act: -0.1700
Data Index: 4243308 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.9304. Min Act: -0.1700
Data Index: 4870590 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.9616. Min Act: -0.1700
Data Index: 6077887 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.9304. Min Act: -0.1699
Data Index: 2137171 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.9304. Min Act: -0.1700
Data Index: 1416294 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.8991. Min Act: -0.1700
Data Index: 2748261 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.8991. Min Act: -0.1700
Data Index: 1196180 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.8679. Min Act: -0.1700
Data Index: 8485917 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.8991. Min Act: -0.1700
Data Index: 6901215 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.8679. Min Act: -0.1700
Data Index: 6594006 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.8366. Min Act: -0.1700
Data Index: 2374551 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.8679. Min Act: -0.1700
Data Index: 498767 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.8679. Min Act: -0.1700
Data Index: 1330507 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.8366. Min Act: -0.1700
Data Index: 7516339 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.8679. Min Act: -0.1700
Data Index: 7300042 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.8366. Min Act: -0.1700
Data Index: 2412684 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2741. Min Range: -5.2741
Max Act: 4.8366. Min Act: -0.1700
Data Index: 6889670 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19