Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 683 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3360. Min Range: -7.3360
Max Act: 7.3360. Min Act: -0.1700
Data Index: 3391572 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3360. Min Range: -7.3360
Max Act: 7.2110. Min Act: -0.1700
Data Index: 7293434 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3360. Min Range: -7.3360
Max Act: 7.0860. Min Act: -0.1700
Data Index: 845699 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3360. Min Range: -7.3360
Max Act: 7.0548. Min Act: -0.1700
Data Index: 4153514 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3360. Min Range: -7.3360
Max Act: 7.0548. Min Act: -0.1700
Data Index: 6875489 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.9923. Min Act: -0.1700
Data Index: 2309787 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.9923. Min Act: -0.1700
Data Index: 4273456 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.9923. Min Act: -0.1700
Data Index: 2454325 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.8985. Min Act: -0.1700
Data Index: 2966864 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.8985. Min Act: -0.1700
Data Index: 6333860 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.8985. Min Act: -0.1700
Data Index: 6591698 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.8985. Min Act: -0.1700
Data Index: 4254944 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.8673. Min Act: -0.1700
Data Index: 7518879 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.8360. Min Act: -0.1700
Data Index: 5320368 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.8673. Min Act: -0.1700
Data Index: 866651 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.8360. Min Act: -0.1700
Data Index: 2759732 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.8048. Min Act: -0.1700
Data Index: 5074465 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.8048. Min Act: -0.1700
Data Index: 4247234 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.8048. Min Act: -0.1700
Data Index: 148908 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3360. Min Range: -7.3360
Max Act: 6.8048. Min Act: -0.1700
Data Index: 4016940 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19