Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4085 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.7330. Min Range: -12.7330
Max Act: 12.7330. Min Act: -0.1700
Data Index: 6843390 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7330. Min Range: -12.7330
Max Act: 11.1080. Min Act: -0.1700
Data Index: 204308 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7330. Min Range: -12.7330
Max Act: 11.6705. Min Act: -0.1700
Data Index: 3856009 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7330. Min Range: -12.7330
Max Act: 9.8580. Min Act: -0.1700
Data Index: 5004800 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7330. Min Range: -12.7330
Max Act: 11.0455. Min Act: -0.1700
Data Index: 1632737 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7330. Min Range: -12.7330
Max Act: 11.4205. Min Act: -0.1700
Data Index: 1820630 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7330. Min Range: -12.7330
Max Act: 10.1080. Min Act: -0.1700
Data Index: 1952644 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7330. Min Range: -12.7330
Max Act: 9.5455. Min Act: -0.1700
Data Index: 7599909 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7330. Min Range: -12.7330
Max Act: 10.6705. Min Act: -0.1700
Data Index: 8330790 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7330. Min Range: -12.7330
Max Act: 10.4205. Min Act: -0.1700
Data Index: 1004253 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7330. Min Range: -12.7330
Max Act: 10.7955. Min Act: -0.1700
Data Index: 3203152 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7330. Min Range: -12.7330
Max Act: 10.2955. Min Act: -0.1700
Data Index: 4389976 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7330. Min Range: -12.7330
Max Act: 10.6080. Min Act: -0.1700
Data Index: 4293929 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7330. Min Range: -12.7330
Max Act: 10.5455. Min Act: -0.1700
Data Index: 6691951 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7330. Min Range: -12.7330
Max Act: 9.4830. Min Act: -0.1700
Data Index: 4539914 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7330. Min Range: -12.7330
Max Act: 10.4205. Min Act: -0.1700
Data Index: 1632736 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7330. Min Range: -12.7330
Max Act: 10.2955. Min Act: -0.1700
Data Index: 6473320 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7330. Min Range: -12.7330
Max Act: 9.1080. Min Act: -0.1700
Data Index: 1606871 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7330. Min Range: -12.7330
Max Act: 9.5455. Min Act: -0.1700
Data Index: 4496132 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7330. Min Range: -12.7330
Max Act: 8.7955. Min Act: -0.1700
Data Index: 350801 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19