Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.4861. Min Act: -0.1700
Data Index: 7629945 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.3299. Min Act: -0.1700
Data Index: 1275159 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.2986. Min Act: -0.1700
Data Index: 1275158 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.2361. Min Act: -0.1700
Data Index: 1275144 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.2049. Min Act: -0.1700
Data Index: 665668 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.2674. Min Act: -0.1700
Data Index: 1275118 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.1736. Min Act: -0.1700
Data Index: 1275135 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.1424. Min Act: -0.1700
Data Index: 1275161 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.1424. Min Act: -0.1700
Data Index: 1275130 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.1111. Min Act: -0.1700
Data Index: 1275121 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.0799. Min Act: -0.1700
Data Index: 1275141 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.0799. Min Act: -0.1700
Data Index: 1275128 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.0174. Min Act: -0.1700
Data Index: 1275143 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.0174. Min Act: -0.1700
Data Index: 5916078 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.0174. Min Act: -0.1700
Data Index: 1275157 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.0174. Min Act: -0.1700
Data Index: 8531092 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.0174. Min Act: -0.1700
Data Index: 3034649 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.0174. Min Act: -0.1700
Data Index: 1275132 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4861. Min Range: -6.4861
Max Act: 6.0486. Min Act: -0.1699
Data Index: 1275147 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4861. Min Range: -6.4861
Max Act: 5.9861. Min Act: -0.1700
Data Index: 1275115 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19