Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2600 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0984. Min Range: -9.0984
Max Act: 9.0984. Min Act: -0.1700
Data Index: 4294040 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0984. Min Range: -9.0984
Max Act: 9.0359. Min Act: -0.1700
Data Index: 49869 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.7859. Min Act: -0.1700
Data Index: 3539191 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.7859. Min Act: -0.1700
Data Index: 863445 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.6609. Min Act: -0.1700
Data Index: 4175250 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.6609. Min Act: -0.1700
Data Index: 8729259 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.5359. Min Act: -0.1700
Data Index: 5209170 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.5984. Min Act: -0.1700
Data Index: 5323666 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.5984. Min Act: -0.1700
Data Index: 2630858 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.5984. Min Act: -0.1700
Data Index: 4310107 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.4734. Min Act: -0.1700
Data Index: 402953 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.4734. Min Act: -0.1700
Data Index: 6180532 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.4734. Min Act: -0.1700
Data Index: 5533002 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.4734. Min Act: -0.1700
Data Index: 2859518 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.4109. Min Act: -0.1700
Data Index: 1375643 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.3484. Min Act: -0.1700
Data Index: 7022862 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.3484. Min Act: -0.1700
Data Index: 2733934 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.2859. Min Act: -0.1700
Data Index: 7105516 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.2859. Min Act: -0.1700
Data Index: 1695605 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0984. Min Range: -9.0984
Max Act: 8.3484. Min Act: -0.1700
Data Index: 204812 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19