Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.7990. Min Act: -0.1700
Data Index: 3735156 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.6427. Min Act: -0.1700
Data Index: 8171424 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.6115. Min Act: -0.1700
Data Index: 2075306 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.6115. Min Act: -0.1700
Data Index: 6612027 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.5802. Min Act: -0.1700
Data Index: 8814843 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.6115. Min Act: -0.1700
Data Index: 955088 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.5490. Min Act: -0.1700
Data Index: 6208548 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.5490. Min Act: -0.1700
Data Index: 2569023 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.4865. Min Act: -0.1700
Data Index: 6478395 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.4865. Min Act: -0.1700
Data Index: 6378396 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.4865. Min Act: -0.1700
Data Index: 1424340 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.4865. Min Act: -0.1700
Data Index: 6465215 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.4865. Min Act: -0.1700
Data Index: 5847636 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.4552. Min Act: -0.1700
Data Index: 5746799 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.4865. Min Act: -0.1700
Data Index: 3699325 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.4865. Min Act: -0.1700
Data Index: 8194861 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.4865. Min Act: -0.1700
Data Index: 2679899 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.4240. Min Act: -0.1700
Data Index: 5692127 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.4552. Min Act: -0.1700
Data Index: 3931580 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7990. Min Range: -4.7990
Max Act: 4.4552. Min Act: -0.1700
Data Index: 4818326 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19