Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5043 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9912. Min Range: -7.9912
Max Act: 7.9912. Min Act: -0.1700
Data Index: 4518640 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9912. Min Range: -7.9912
Max Act: 7.9287. Min Act: -0.1700
Data Index: 8034081 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9912. Min Range: -7.9912
Max Act: 7.7725. Min Act: -0.1700
Data Index: 5106274 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9912. Min Range: -7.9912
Max Act: 7.3350. Min Act: -0.1700
Data Index: 3987583 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9912. Min Range: -7.9912
Max Act: 7.3037. Min Act: -0.1700
Data Index: 6960239 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9912. Min Range: -7.9912
Max Act: 7.2412. Min Act: -0.1700
Data Index: 5331606 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9912. Min Range: -7.9912
Max Act: 7.2412. Min Act: -0.1700
Data Index: 6021910 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9912. Min Range: -7.9912
Max Act: 7.1787. Min Act: -0.1700
Data Index: 1890914 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9912. Min Range: -7.9912
Max Act: 7.0225. Min Act: -0.1700
Data Index: 3206619 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9912. Min Range: -7.9912
Max Act: 6.9600. Min Act: -0.1700
Data Index: 966604 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9912. Min Range: -7.9912
Max Act: 6.9287. Min Act: -0.1700
Data Index: 6059932 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9912. Min Range: -7.9912
Max Act: 6.8662. Min Act: -0.1700
Data Index: 6837458 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9912. Min Range: -7.9912
Max Act: 6.8662. Min Act: -0.1700
Data Index: 616785 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9912. Min Range: -7.9912
Max Act: 6.8662. Min Act: -0.1700
Data Index: 5815214 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9912. Min Range: -7.9912
Max Act: 6.8037. Min Act: -0.1700
Data Index: 7543141 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9912. Min Range: -7.9912
Max Act: 6.8037. Min Act: -0.1700
Data Index: 5065806 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9912. Min Range: -7.9912
Max Act: 6.8037. Min Act: -0.1700
Data Index: 7458835 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9912. Min Range: -7.9912
Max Act: 6.8037. Min Act: -0.1700
Data Index: 743116 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9912. Min Range: -7.9912
Max Act: 6.7725. Min Act: -0.1700
Data Index: 3149607 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9912. Min Range: -7.9912
Max Act: 6.7412. Min Act: -0.1700
Data Index: 1868322 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19