Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3821 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.4244. Min Act: -0.1700
Data Index: 6429850 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.3619. Min Act: -0.1700
Data Index: 1459969 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.1432. Min Act: -0.1700
Data Index: 1459972 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.1432. Min Act: -0.1700
Data Index: 3306551 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.1432. Min Act: -0.1700
Data Index: 3306546 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.1119. Min Act: -0.1700
Data Index: 5911661 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.0494. Min Act: -0.1700
Data Index: 611444 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.0807. Min Act: -0.1700
Data Index: 7668346 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.1119. Min Act: -0.1700
Data Index: 7306075 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.0494. Min Act: -0.1700
Data Index: 2823757 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.0494. Min Act: -0.1700
Data Index: 6853668 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.0494. Min Act: -0.1700
Data Index: 5668039 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.0182. Min Act: -0.1700
Data Index: 4945571 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4244. Min Range: -7.4244
Max Act: 6.9557. Min Act: -0.1700
Data Index: 1570475 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.0182. Min Act: -0.1700
Data Index: 6937409 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4244. Min Range: -7.4244
Max Act: 6.9869. Min Act: -0.1700
Data Index: 6503590 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4244. Min Range: -7.4244
Max Act: 6.9869. Min Act: -0.1700
Data Index: 1154067 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4244. Min Range: -7.4244
Max Act: 6.9869. Min Act: -0.1700
Data Index: 2973818 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4244. Min Range: -7.4244
Max Act: 7.0182. Min Act: -0.1700
Data Index: 1161281 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4244. Min Range: -7.4244
Max Act: 6.9557. Min Act: -0.1700
Data Index: 2231269 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19