Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4639 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.6625. Min Act: -0.1700
Data Index: 2479219 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.6000. Min Act: -0.1700
Data Index: 3917818 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.5687. Min Act: -0.1700
Data Index: 2564745 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.5375. Min Act: -0.1700
Data Index: 3260960 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.5375. Min Act: -0.1700
Data Index: 727407 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.5375. Min Act: -0.1700
Data Index: 8614409 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.5375. Min Act: -0.1700
Data Index: 2879056 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.5375. Min Act: -0.1700
Data Index: 6876582 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.5375. Min Act: -0.1700
Data Index: 1921031 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.5375. Min Act: -0.1700
Data Index: 6331929 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.4750. Min Act: -0.1700
Data Index: 530544 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.5062. Min Act: -0.1699
Data Index: 7956238 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.5062. Min Act: -0.1700
Data Index: 8109306 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.4750. Min Act: -0.1700
Data Index: 599189 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.5062. Min Act: -0.1700
Data Index: 6826154 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.5062. Min Act: -0.1697
Data Index: 5877671 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.4750. Min Act: -0.1700
Data Index: 4479547 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.4750. Min Act: -0.1700
Data Index: 5154640 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.5062. Min Act: -0.1700
Data Index: 7238038 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6625. Min Range: -5.6625
Max Act: 5.4750. Min Act: -0.1700
Data Index: 5947568 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19