Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1372. Min Range: -6.1372
Max Act: 6.1372. Min Act: -0.1700
Data Index: 723914 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.9810. Min Act: -0.1700
Data Index: 2495610 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.9810. Min Act: -0.1700
Data Index: 1032902 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.9497. Min Act: -0.1700
Data Index: 5644050 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.8872. Min Act: -0.1700
Data Index: 5152487 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.9185. Min Act: -0.1700
Data Index: 1059750 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.8872. Min Act: -0.1700
Data Index: 3388555 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.8560. Min Act: -0.1700
Data Index: 4252557 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.8872. Min Act: -0.1700
Data Index: 6475815 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.8560. Min Act: -0.1700
Data Index: 4958093 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.7935. Min Act: -0.1700
Data Index: 5310538 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.8560. Min Act: -0.1700
Data Index: 5876753 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.8247. Min Act: -0.1700
Data Index: 3896971 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.8247. Min Act: -0.1700
Data Index: 8768071 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.7935. Min Act: -0.1700
Data Index: 844767 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.7935. Min Act: -0.1700
Data Index: 8458643 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.7935. Min Act: -0.1700
Data Index: 2863296 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.8247. Min Act: -0.1700
Data Index: 1847599 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.8247. Min Act: -0.1700
Data Index: 3921802 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1372. Min Range: -6.1372
Max Act: 5.7622. Min Act: -0.1700
Data Index: 3786584 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19