Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3610 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.7026. Min Act: -0.1700
Data Index: 4741551 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.7026. Min Act: -0.1700
Data Index: 2158451 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.5776. Min Act: -0.1700
Data Index: 337728 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.5151. Min Act: -0.1700
Data Index: 5887052 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.3901. Min Act: -0.1700
Data Index: 1066635 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.3901. Min Act: -0.1700
Data Index: 8304873 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.3901. Min Act: -0.1700
Data Index: 545522 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.3901. Min Act: -0.1700
Data Index: 4495431 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.2651. Min Act: -0.1700
Data Index: 2255855 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.2026. Min Act: -0.1700
Data Index: 1015764 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.2026. Min Act: -0.1700
Data Index: 3425818 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.2026. Min Act: -0.1700
Data Index: 267870 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.2026. Min Act: -0.1700
Data Index: 8714711 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.2026. Min Act: -0.1700
Data Index: 7836720 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.1401. Min Act: -0.1700
Data Index: 2781131 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.0776. Min Act: -0.1700
Data Index: 4753729 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.0776. Min Act: -0.1700
Data Index: 4501272 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.0776. Min Act: -0.1700
Data Index: 1987229 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.0776. Min Act: -0.1700
Data Index: 5989262 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7026. Min Range: -8.7026
Max Act: 8.0776. Min Act: -0.1700
Data Index: 2177764 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19