Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3179 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2837. Min Range: -7.2837
Max Act: 7.2837. Min Act: -0.1700
Data Index: 8284352 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2837. Min Range: -7.2837
Max Act: 7.2525. Min Act: -0.1700
Data Index: 6514442 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2837. Min Range: -7.2837
Max Act: 7.0650. Min Act: -0.1700
Data Index: 449217 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.9087. Min Act: -0.1700
Data Index: 5325855 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.8462. Min Act: -0.1700
Data Index: 6957977 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.8462. Min Act: -0.1700
Data Index: 4098495 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.7212. Min Act: -0.1700
Data Index: 1583006 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.6900. Min Act: -0.1700
Data Index: 6189053 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.6587. Min Act: -0.1700
Data Index: 8174082 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.6275. Min Act: -0.1700
Data Index: 3353558 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.6275. Min Act: -0.1700
Data Index: 5970646 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.6275. Min Act: -0.1700
Data Index: 6644039 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.6275. Min Act: -0.1700
Data Index: 4986983 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.6275. Min Act: -0.1700
Data Index: 1409815 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.5962. Min Act: -0.1700
Data Index: 7252608 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.5962. Min Act: -0.1700
Data Index: 8782115 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.5337. Min Act: -0.1700
Data Index: 3446912 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.5337. Min Act: -0.1700
Data Index: 3905432 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.4712. Min Act: -0.1700
Data Index: 3919280 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2837. Min Range: -7.2837
Max Act: 6.5025. Min Act: -0.1700
Data Index: 3739922 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19