Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 730 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.3559. Min Act: -0.1700
Data Index: 6274650 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.2934. Min Act: -0.1700
Data Index: 7368017 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.1996. Min Act: -0.1700
Data Index: 4866108 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.1996. Min Act: -0.1700
Data Index: 6064500 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.1371. Min Act: -0.1700
Data Index: 1274589 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.1059. Min Act: -0.1700
Data Index: 2762056 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.1371. Min Act: -0.1700
Data Index: 2609698 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.1059. Min Act: -0.1700
Data Index: 7394439 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.0746. Min Act: -0.1700
Data Index: 4996566 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.0434. Min Act: -0.1700
Data Index: 8773950 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.0434. Min Act: -0.1700
Data Index: 8089550 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.0434. Min Act: -0.1700
Data Index: 3949224 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.0121. Min Act: -0.1700
Data Index: 6955796 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3559. Min Range: -5.3559
Max Act: 4.9809. Min Act: -0.1700
Data Index: 5027611 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.0434. Min Act: -0.1700
Data Index: 4490730 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3559. Min Range: -5.3559
Max Act: 4.9809. Min Act: -0.1700
Data Index: 1016093 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3559. Min Range: -5.3559
Max Act: 5.0121. Min Act: -0.1700
Data Index: 6430071 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3559. Min Range: -5.3559
Max Act: 4.9809. Min Act: -0.1700
Data Index: 6986196 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3559. Min Range: -5.3559
Max Act: 4.9809. Min Act: -0.1700
Data Index: 7197175 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3559. Min Range: -5.3559
Max Act: 4.9809. Min Act: -0.1700
Data Index: 5205543 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19