Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.2849. Min Act: -0.1700
Data Index: 5839555 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0661. Min Act: -0.1700
Data Index: 2575289 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0348. Min Act: -0.1700
Data Index: 8290088 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0036. Min Act: -0.1700
Data Index: 7215670 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0036. Min Act: -0.1700
Data Index: 8160579 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.9723. Min Act: -0.1700
Data Index: 6528538 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.9410. Min Act: -0.1700
Data Index: 1417742 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.9410. Min Act: -0.1700
Data Index: 572534 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.9098. Min Act: -0.1700
Data Index: 167043 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.9098. Min Act: -0.1700
Data Index: 5687195 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.9098. Min Act: -0.1700
Data Index: 7307429 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.9098. Min Act: -0.1700
Data Index: 992371 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.8472. Min Act: -0.1700
Data Index: 635418 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.8785. Min Act: -0.1700
Data Index: 691112 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.8785. Min Act: -0.1700
Data Index: 7313503 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.8785. Min Act: -0.1700
Data Index: 7095712 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.8785. Min Act: -0.1700
Data Index: 5478987 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.8785. Min Act: -0.1700
Data Index: 1285529 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.8785. Min Act: -0.1700
Data Index: 7727307 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2849. Min Range: -4.2849
Max Act: 3.8785. Min Act: -0.1700
Data Index: 1083586 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19