Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2860 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3972. Min Range: -7.3972
Max Act: 7.3972. Min Act: -0.1700
Data Index: 1145858 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3972. Min Range: -7.3972
Max Act: 7.3972. Min Act: -0.1700
Data Index: 5919180 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3972. Min Range: -7.3972
Max Act: 7.2410. Min Act: -0.1700
Data Index: 4409235 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3972. Min Range: -7.3972
Max Act: 7.1785. Min Act: -0.1700
Data Index: 6930678 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3972. Min Range: -7.3972
Max Act: 7.1785. Min Act: -0.1700
Data Index: 1145861 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3972. Min Range: -7.3972
Max Act: 7.1785. Min Act: -0.1700
Data Index: 471700 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3972. Min Range: -7.3972
Max Act: 7.1160. Min Act: -0.1700
Data Index: 2665303 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3972. Min Range: -7.3972
Max Act: 7.1160. Min Act: -0.1700
Data Index: 471702 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3972. Min Range: -7.3972
Max Act: 7.1472. Min Act: -0.1700
Data Index: 471699 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3972. Min Range: -7.3972
Max Act: 7.0535. Min Act: -0.1700
Data Index: 6688297 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3972. Min Range: -7.3972
Max Act: 7.0847. Min Act: -0.1700
Data Index: 6930676 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3972. Min Range: -7.3972
Max Act: 7.0535. Min Act: -0.1700
Data Index: 4409240 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3972. Min Range: -7.3972
Max Act: 7.0222. Min Act: -0.1700
Data Index: 2611149 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3972. Min Range: -7.3972
Max Act: 6.9910. Min Act: -0.1700
Data Index: 6930677 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3972. Min Range: -7.3972
Max Act: 6.9597. Min Act: -0.1700
Data Index: 5080091 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3972. Min Range: -7.3972
Max Act: 6.9910. Min Act: -0.1700
Data Index: 2592688 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3972. Min Range: -7.3972
Max Act: 6.9597. Min Act: -0.1700
Data Index: 2611151 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3972. Min Range: -7.3972
Max Act: 6.9285. Min Act: -0.1700
Data Index: 1145860 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3972. Min Range: -7.3972
Max Act: 6.9285. Min Act: -0.1700
Data Index: 1145859 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3972. Min Range: -7.3972
Max Act: 6.9597. Min Act: -0.1700
Data Index: 2594297 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19