Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.3754. Min Act: -0.1700
Data Index: 4556344 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.3441. Min Act: -0.1700
Data Index: 7998962 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.2816. Min Act: -0.1700
Data Index: 8362271 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.1566. Min Act: -0.1700
Data Index: 5881379 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.1566. Min Act: -0.1700
Data Index: 2811967 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.1566. Min Act: -0.1700
Data Index: 5670803 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.1254. Min Act: -0.1700
Data Index: 8161677 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.1254. Min Act: -0.1700
Data Index: 3680669 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.1254. Min Act: -0.1700
Data Index: 7580791 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.1254. Min Act: -0.1700
Data Index: 6201912 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.1254. Min Act: -0.1700
Data Index: 7541087 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.0629. Min Act: -0.1700
Data Index: 3733648 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.0629. Min Act: -0.1700
Data Index: 7194724 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.0629. Min Act: -0.1700
Data Index: 3421697 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3754. Min Range: -6.3754
Max Act: 5.9691. Min Act: -0.1700
Data Index: 7543795 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3754. Min Range: -6.3754
Max Act: 5.9691. Min Act: -0.1700
Data Index: 2783989 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3754. Min Range: -6.3754
Max Act: 5.9379. Min Act: -0.1700
Data Index: 6829552 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3754. Min Range: -6.3754
Max Act: 5.9379. Min Act: -0.1700
Data Index: 446856 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3754. Min Range: -6.3754
Max Act: 5.9379. Min Act: -0.1700
Data Index: 8049252 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3754. Min Range: -6.3754
Max Act: 5.9066. Min Act: -0.1700
Data Index: 3846584 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19