Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6107 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.6715. Min Act: -0.1700
Data Index: 4195463 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5153. Min Act: -0.1700
Data Index: 4086423 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.5153. Min Act: -0.1700
Data Index: 6261193 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.4528. Min Act: -0.1700
Data Index: 8357025 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.3590. Min Act: -0.1700
Data Index: 4371034 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.3903. Min Act: -0.1700
Data Index: 1030550 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.2965. Min Act: -0.1698
Data Index: 3768708 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.3278. Min Act: -0.1700
Data Index: 5971678 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.2965. Min Act: -0.1700
Data Index: 1628086 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.2965. Min Act: -0.1700
Data Index: 443372 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.2965. Min Act: -0.1700
Data Index: 3610006 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.2965. Min Act: -0.1700
Data Index: 1286655 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.2653. Min Act: -0.1700
Data Index: 2270672 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.2653. Min Act: -0.1700
Data Index: 6083862 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.2653. Min Act: -0.1700
Data Index: 2976958 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.2653. Min Act: -0.1700
Data Index: 5279990 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.2653. Min Act: -0.1700
Data Index: 7980525 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.2653. Min Act: -0.1700
Data Index: 5073526 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.2340. Min Act: -0.1700
Data Index: 7496047 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6715. Min Range: -5.6715
Max Act: 5.2653. Min Act: -0.1700
Data Index: 7205165 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19