Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2171 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.7858. Min Act: -0.1700
Data Index: 7565139 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.7233. Min Act: -0.1700
Data Index: 1133183 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.5983. Min Act: -0.1700
Data Index: 7387734 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.5046. Min Act: -0.1700
Data Index: 7291724 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.4421. Min Act: -0.1700
Data Index: 1509119 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.4421. Min Act: -0.1700
Data Index: 277288 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.3796. Min Act: -0.1700
Data Index: 6517075 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.3171. Min Act: -0.1700
Data Index: 5670509 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.3171. Min Act: -0.1700
Data Index: 5616489 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.2858. Min Act: -0.1700
Data Index: 2180312 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.2858. Min Act: -0.1700
Data Index: 2703527 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.2858. Min Act: -0.1700
Data Index: 322855 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.2858. Min Act: -0.1700
Data Index: 8581355 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.2546. Min Act: -0.1700
Data Index: 2921268 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.2546. Min Act: -0.1700
Data Index: 5991738 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.2233. Min Act: -0.1700
Data Index: 4275770 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.2233. Min Act: -0.1700
Data Index: 5522505 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.2233. Min Act: -0.1700
Data Index: 2829869 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.1921. Min Act: -0.1700
Data Index: 4229419 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.2233. Min Act: -0.1700
Data Index: 5914547 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19