Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4706 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.6043. Min Act: -0.1700
Data Index: 657913 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.5418. Min Act: -0.1700
Data Index: 2388991 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.5418. Min Act: -0.1700
Data Index: 3581125 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.4793. Min Act: -0.1700
Data Index: 8711899 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.4793. Min Act: -0.1700
Data Index: 7749485 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.3543. Min Act: -0.1700
Data Index: 3234847 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.4168. Min Act: -0.1700
Data Index: 2341304 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.3543. Min Act: -0.1700
Data Index: 2261836 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.2918. Min Act: -0.1700
Data Index: 5286679 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.2918. Min Act: -0.1700
Data Index: 866424 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.2293. Min Act: -0.1700
Data Index: 5153288 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.2293. Min Act: -0.1700
Data Index: 6985426 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.1668. Min Act: -0.1700
Data Index: 4068293 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.1668. Min Act: -0.1700
Data Index: 2341308 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.1668. Min Act: -0.1700
Data Index: 1869909 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.1043. Min Act: -0.1700
Data Index: 345103 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.1043. Min Act: -0.1700
Data Index: 7217095 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.1043. Min Act: -0.1700
Data Index: 8464751 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.0418. Min Act: -0.1700
Data Index: 5740227 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6043. Min Range: -10.6043
Max Act: 10.0418. Min Act: -0.1700
Data Index: 3777359 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19