Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2859 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0301. Min Range: -6.0301
Max Act: 6.0301. Min Act: -0.1700
Data Index: 5519329 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.9989. Min Act: -0.1700
Data Index: 2686417 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.9989. Min Act: -0.1700
Data Index: 8547577 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.9676. Min Act: -0.1700
Data Index: 8541233 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.9676. Min Act: -0.1700
Data Index: 809962 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.9364. Min Act: -0.1700
Data Index: 809194 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.9364. Min Act: -0.1700
Data Index: 5855770 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.9364. Min Act: -0.1700
Data Index: 661007 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.9051. Min Act: -0.1700
Data Index: 196193 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.8739. Min Act: -0.1700
Data Index: 3693436 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.8426. Min Act: -0.1700
Data Index: 3156999 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.8426. Min Act: -0.1700
Data Index: 8054364 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.8114. Min Act: -0.1700
Data Index: 7243647 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.8426. Min Act: -0.1700
Data Index: 6031339 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.8114. Min Act: -0.1700
Data Index: 6033306 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.7801. Min Act: -0.1700
Data Index: 7715244 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.7801. Min Act: -0.1700
Data Index: 2935074 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.7489. Min Act: -0.1700
Data Index: 5845517 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.7489. Min Act: -0.1700
Data Index: 5896627 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0301. Min Range: -6.0301
Max Act: 5.7176. Min Act: -0.1700
Data Index: 6049629 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19