Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1607 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0100. Min Range: -6.0100
Max Act: 6.0100. Min Act: -0.1700
Data Index: 8646652 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0100. Min Range: -6.0100
Max Act: 6.0100. Min Act: -0.1700
Data Index: 8589720 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.7912. Min Act: -0.1700
Data Index: 4575068 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.7600. Min Act: -0.1700
Data Index: 6808826 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.7287. Min Act: -0.1700
Data Index: 8382721 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.6975. Min Act: -0.1700
Data Index: 7135066 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.6662. Min Act: -0.1700
Data Index: 1948853 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.6662. Min Act: -0.1700
Data Index: 3910266 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.6662. Min Act: -0.1700
Data Index: 2110087 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.6350. Min Act: -0.1700
Data Index: 7666791 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.6037. Min Act: -0.1700
Data Index: 2618577 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.6037. Min Act: -0.1700
Data Index: 3967895 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.6037. Min Act: -0.1700
Data Index: 8587316 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.5725. Min Act: -0.1700
Data Index: 897581 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.5725. Min Act: -0.1700
Data Index: 387113 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.5412. Min Act: -0.1700
Data Index: 6566698 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.5412. Min Act: -0.1700
Data Index: 3767766 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.5412. Min Act: -0.1700
Data Index: 6219115 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.5412. Min Act: -0.1700
Data Index: 6175217 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0100. Min Range: -6.0100
Max Act: 5.5412. Min Act: -0.1700
Data Index: 7096490 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19