Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 868 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2134. Min Range: -4.2134
Max Act: 4.2134. Min Act: -0.1700
Data Index: 5621846 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2134. Min Range: -4.2134
Max Act: 4.1509. Min Act: -0.1700
Data Index: 6231442 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2134. Min Range: -4.2134
Max Act: 4.0571. Min Act: -0.1700
Data Index: 1934851 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.9946. Min Act: -0.1700
Data Index: 6535757 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.9946. Min Act: -0.1700
Data Index: 7656513 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.9321. Min Act: -0.1700
Data Index: 7039803 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.9321. Min Act: -0.1700
Data Index: 2089838 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.9321. Min Act: -0.1700
Data Index: 4113408 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.8695. Min Act: -0.1700
Data Index: 7963876 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.8695. Min Act: -0.1700
Data Index: 4426656 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.8695. Min Act: -0.1700
Data Index: 5412937 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.8695. Min Act: -0.1700
Data Index: 1313353 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.8383. Min Act: -0.1700
Data Index: 434416 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.8383. Min Act: -0.1700
Data Index: 4847240 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.8383. Min Act: -0.1700
Data Index: 3227413 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.8383. Min Act: -0.1700
Data Index: 402086 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.8383. Min Act: -0.1700
Data Index: 3160756 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.8383. Min Act: -0.1700
Data Index: 3311256 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.8070. Min Act: -0.1700
Data Index: 5301912 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2134. Min Range: -4.2134
Max Act: 3.7757. Min Act: -0.1700
Data Index: 789990 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19