Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.7483. Min Act: -0.1700
Data Index: 3592839 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.7171. Min Act: -0.1700
Data Index: 7006048 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.7171. Min Act: -0.1700
Data Index: 6874077 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.7171. Min Act: -0.1700
Data Index: 2279793 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.6546. Min Act: -0.1700
Data Index: 543950 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.6858. Min Act: -0.1700
Data Index: 7072353 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.6858. Min Act: -0.1700
Data Index: 1127995 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.6858. Min Act: -0.1700
Data Index: 4065669 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.6546. Min Act: -0.1700
Data Index: 374087 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.6233. Min Act: -0.1700
Data Index: 3439810 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.5921. Min Act: -0.1700
Data Index: 6828952 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.6233. Min Act: -0.1700
Data Index: 5864934 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.6233. Min Act: -0.1700
Data Index: 5476444 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.5921. Min Act: -0.1700
Data Index: 3937457 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.5921. Min Act: -0.1700
Data Index: 2968686 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.5921. Min Act: -0.1700
Data Index: 6365843 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.5921. Min Act: -0.1700
Data Index: 3574904 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.5608. Min Act: -0.1700
Data Index: 930935 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.5608. Min Act: -0.1700
Data Index: 8415533 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7483. Min Range: -5.7483
Max Act: 5.5921. Min Act: -0.1700
Data Index: 6551115 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19