Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.9101. Min Act: -0.1700
Data Index: 3679246 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.7851. Min Act: -0.1700
Data Index: 4609703 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.7538. Min Act: -0.1700
Data Index: 849269 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.6913. Min Act: -0.1700
Data Index: 2037948 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.5976. Min Act: -0.1700
Data Index: 2878907 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.5663. Min Act: -0.1700
Data Index: 3540586 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.5351. Min Act: -0.1700
Data Index: 1867450 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.5663. Min Act: -0.1700
Data Index: 5890992 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.5038. Min Act: -0.1700
Data Index: 4755672 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.5038. Min Act: -0.1700
Data Index: 5790127 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.3476. Min Act: -0.1700
Data Index: 3757875 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.2538. Min Act: -0.1700
Data Index: 7703614 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.1913. Min Act: -0.1700
Data Index: 6733618 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.1601. Min Act: -0.1700
Data Index: 7376464 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.1913. Min Act: -0.1700
Data Index: 7921664 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.1913. Min Act: -0.1700
Data Index: 8325892 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.1601. Min Act: -0.1700
Data Index: 6658215 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.1601. Min Act: -0.1700
Data Index: 4538082 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.1288. Min Act: -0.1700
Data Index: 4899695 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9101. Min Range: -7.9101
Max Act: 7.1288. Min Act: -0.1700
Data Index: 5295442 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19