Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3163 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2880. Min Range: -9.2880
Max Act: 9.2880. Min Act: -0.1700
Data Index: 1124176 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.9755. Min Act: -0.1700
Data Index: 2911994 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.8505. Min Act: -0.1700
Data Index: 5412894 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.6630. Min Act: -0.1700
Data Index: 3938075 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.6005. Min Act: -0.1700
Data Index: 4045604 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.5380. Min Act: -0.1700
Data Index: 4121287 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.5380. Min Act: -0.1700
Data Index: 4550848 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.4755. Min Act: -0.1700
Data Index: 8380134 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.5380. Min Act: -0.1700
Data Index: 4121298 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.5380. Min Act: -0.1700
Data Index: 1607122 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.4755. Min Act: -0.1700
Data Index: 7551780 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.4755. Min Act: -0.1700
Data Index: 1441620 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.4755. Min Act: -0.1700
Data Index: 4011356 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.4755. Min Act: -0.1700
Data Index: 4045601 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.4755. Min Act: -0.1700
Data Index: 364703 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.4130. Min Act: -0.1700
Data Index: 1601975 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.4130. Min Act: -0.1700
Data Index: 2755681 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.4130. Min Act: -0.1700
Data Index: 7919311 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.3505. Min Act: -0.1700
Data Index: 3769298 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2880. Min Range: -9.2880
Max Act: 8.3505. Min Act: -0.1700
Data Index: 1805678 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19