Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 956 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.7995. Min Act: -0.1700
Data Index: 6946419 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.7370. Min Act: -0.1700
Data Index: 8066545 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.5807. Min Act: -0.1700
Data Index: 4348431 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.4870. Min Act: -0.1700
Data Index: 8027105 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.4557. Min Act: -0.1700
Data Index: 3119163 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.4245. Min Act: -0.1700
Data Index: 619063 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.3307. Min Act: -0.1700
Data Index: 4623262 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.3620. Min Act: -0.1700
Data Index: 3944775 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.3620. Min Act: -0.1700
Data Index: 4074765 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.3932. Min Act: -0.1700
Data Index: 2236101 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.3620. Min Act: -0.1700
Data Index: 2444520 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.3307. Min Act: -0.1700
Data Index: 2533444 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.3307. Min Act: -0.1700
Data Index: 120997 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.2682. Min Act: -0.1700
Data Index: 6956295 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.2682. Min Act: -0.1700
Data Index: 8587538 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.2682. Min Act: -0.1700
Data Index: 3379770 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.2370. Min Act: -0.1700
Data Index: 1615218 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.2370. Min Act: -0.1700
Data Index: 1185842 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.2370. Min Act: -0.1700
Data Index: 2664185 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7995. Min Range: -6.7995
Max Act: 6.2057. Min Act: -0.1700
Data Index: 8393397 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19