Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4774 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.9320. Min Act: -0.1700
Data Index: 6149041 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.9320. Min Act: -0.1700
Data Index: 5608239 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.9320. Min Act: -0.1700
Data Index: 4006859 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.8070. Min Act: -0.1700
Data Index: 6618662 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.7445. Min Act: -0.1700
Data Index: 175646 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.7133. Min Act: -0.1700
Data Index: 5745433 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.6820. Min Act: -0.1700
Data Index: 3769074 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.6820. Min Act: -0.1700
Data Index: 5144502 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.6820. Min Act: -0.1700
Data Index: 634249 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.6508. Min Act: -0.1700
Data Index: 5949899 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.6508. Min Act: -0.1700
Data Index: 1392077 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.6195. Min Act: -0.1700
Data Index: 6538627 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.6195. Min Act: -0.1700
Data Index: 1887134 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.6195. Min Act: -0.1700
Data Index: 8184437 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.6508. Min Act: -0.1700
Data Index: 6481183 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.5883. Min Act: -0.1700
Data Index: 5405958 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.5883. Min Act: -0.1700
Data Index: 8514986 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.5883. Min Act: -0.1700
Data Index: 1450512 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.5883. Min Act: -0.1700
Data Index: 3580002 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9320. Min Range: -4.9320
Max Act: 4.5570. Min Act: -0.1700
Data Index: 5139761 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19