Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.6746. Min Act: -0.1700
Data Index: 2234612 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.7059. Min Act: -0.1700
Data Index: 5148307 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.6746. Min Act: -0.1700
Data Index: 6021275 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.6746. Min Act: -0.1700
Data Index: 6710254 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.6746. Min Act: -0.1700
Data Index: 4388610 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5809. Min Act: -0.1700
Data Index: 356022 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5496. Min Act: -0.1700
Data Index: 4457069 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5496. Min Act: -0.1700
Data Index: 1888119 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5496. Min Act: -0.1700
Data Index: 1348647 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5496. Min Act: -0.1700
Data Index: 3161060 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5496. Min Act: -0.1697
Data Index: 5781152 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5184. Min Act: -0.1700
Data Index: 649136 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5184. Min Act: -0.1700
Data Index: 2623715 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5184. Min Act: -0.1700
Data Index: 5111862 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5184. Min Act: -0.1700
Data Index: 3003836 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5496. Min Act: -0.1700
Data Index: 5567350 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5184. Min Act: -0.1700
Data Index: 744474 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5184. Min Act: -0.1700
Data Index: 3119981 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5184. Min Act: -0.1700
Data Index: 3206992 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7059. Min Range: -4.7059
Max Act: 4.5184. Min Act: -0.1700
Data Index: 5571695 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19