Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5447 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.8654. Min Act: -0.1700
Data Index: 4049545 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.7717. Min Act: -0.1700
Data Index: 8077571 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.6467. Min Act: -0.1700
Data Index: 2310175 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.5842. Min Act: -0.1700
Data Index: 5236938 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.5842. Min Act: -0.1700
Data Index: 8225760 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.5842. Min Act: -0.1700
Data Index: 292913 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.5529. Min Act: -0.1700
Data Index: 6759789 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.5217. Min Act: -0.1700
Data Index: 7398184 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.5217. Min Act: -0.1700
Data Index: 7798980 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.4904. Min Act: -0.1700
Data Index: 2550970 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.4904. Min Act: -0.1700
Data Index: 6278657 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.4904. Min Act: -0.1700
Data Index: 4960107 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.4592. Min Act: -0.1700
Data Index: 8495332 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.4592. Min Act: -0.1700
Data Index: 8782012 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.4592. Min Act: -0.1700
Data Index: 1556374 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.4279. Min Act: -0.1700
Data Index: 449240 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.4279. Min Act: -0.1700
Data Index: 4387417 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.3966. Min Act: -0.1700
Data Index: 140767 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.3966. Min Act: -0.1700
Data Index: 6026391 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8654. Min Range: -4.8654
Max Act: 4.3966. Min Act: -0.1700
Data Index: 2680394 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19