Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5967. Min Range: -5.5967
Max Act: 5.5967. Min Act: -0.1700
Data Index: 4555485 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5967. Min Range: -5.5967
Max Act: 5.1904. Min Act: -0.1700
Data Index: 7204745 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5967. Min Range: -5.5967
Max Act: 5.0967. Min Act: -0.1700
Data Index: 6343199 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5967. Min Range: -5.5967
Max Act: 5.0967. Min Act: -0.1700
Data Index: 5136839 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5967. Min Range: -5.5967
Max Act: 5.0654. Min Act: -0.1700
Data Index: 2838464 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5967. Min Range: -5.5967
Max Act: 5.0654. Min Act: -0.1700
Data Index: 5628302 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5967. Min Range: -5.5967
Max Act: 5.0654. Min Act: -0.1700
Data Index: 2574058 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5967. Min Range: -5.5967
Max Act: 5.0342. Min Act: -0.1700
Data Index: 1869601 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5967. Min Range: -5.5967
Max Act: 5.0029. Min Act: -0.1700
Data Index: 111505 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5967. Min Range: -5.5967
Max Act: 4.9717. Min Act: -0.1700
Data Index: 8393081 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5967. Min Range: -5.5967
Max Act: 4.9717. Min Act: -0.1700
Data Index: 6179590 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5967. Min Range: -5.5967
Max Act: 4.9404. Min Act: -0.1700
Data Index: 4116298 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5967. Min Range: -5.5967
Max Act: 4.9404. Min Act: -0.1700
Data Index: 1291506 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5967. Min Range: -5.5967
Max Act: 4.9092. Min Act: -0.1700
Data Index: 799757 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5967. Min Range: -5.5967
Max Act: 4.9404. Min Act: -0.1700
Data Index: 5188349 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5967. Min Range: -5.5967
Max Act: 4.9404. Min Act: -0.1700
Data Index: 4442158 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5967. Min Range: -5.5967
Max Act: 4.9404. Min Act: -0.1700
Data Index: 6884622 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5967. Min Range: -5.5967
Max Act: 4.9092. Min Act: -0.1700
Data Index: 979136 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5967. Min Range: -5.5967
Max Act: 4.9092. Min Act: -0.1700
Data Index: 946157 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5967. Min Range: -5.5967
Max Act: 4.9092. Min Act: -0.1700
Data Index: 6698264 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19