Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 31 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1820. Min Range: -6.1820
Max Act: 6.1820. Min Act: -0.1700
Data Index: 5316207 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.5570. Min Act: -0.1700
Data Index: 4654312 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.2757. Min Act: -0.1700
Data Index: 1043894 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.2132. Min Act: -0.1700
Data Index: 194186 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.1507. Min Act: -0.1700
Data Index: 2923231 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.0882. Min Act: -0.1700
Data Index: 3105993 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.0570. Min Act: -0.1700
Data Index: 5065221 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.0257. Min Act: -0.1700
Data Index: 4070324 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1820. Min Range: -6.1820
Max Act: 4.9320. Min Act: -0.1700
Data Index: 5125843 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1820. Min Range: -6.1820
Max Act: 4.9320. Min Act: -0.1700
Data Index: 1851163 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1820. Min Range: -6.1820
Max Act: 4.9320. Min Act: -0.1700
Data Index: 3192617 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1820. Min Range: -6.1820
Max Act: 4.9007. Min Act: -0.1700
Data Index: 8790942 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1820. Min Range: -6.1820
Max Act: 4.8695. Min Act: -0.1700
Data Index: 1253504 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1820. Min Range: -6.1820
Max Act: 4.8382. Min Act: -0.1700
Data Index: 7604960 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1820. Min Range: -6.1820
Max Act: 4.8070. Min Act: -0.1700
Data Index: 7671707 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1820. Min Range: -6.1820
Max Act: 4.8070. Min Act: -0.1700
Data Index: 3068685 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1820. Min Range: -6.1820
Max Act: 4.8382. Min Act: -0.1700
Data Index: 4347580 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1820. Min Range: -6.1820
Max Act: 4.8070. Min Act: -0.1700
Data Index: 5029198 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1820. Min Range: -6.1820
Max Act: 4.7445. Min Act: -0.1700
Data Index: 8106128 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1820. Min Range: -6.1820
Max Act: 4.7445. Min Act: -0.1700
Data Index: 4904667 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19