Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6272 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4039. Min Range: -7.4039
Max Act: 7.4039. Min Act: -0.1700
Data Index: 950466 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.9351. Min Act: -0.1700
Data Index: 1500838 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.9351. Min Act: -0.1700
Data Index: 8352914 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.9039. Min Act: -0.1700
Data Index: 4431167 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.8726. Min Act: -0.1700
Data Index: 2161093 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.8101. Min Act: -0.1700
Data Index: 8147323 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.7789. Min Act: -0.1700
Data Index: 7744693 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.7789. Min Act: -0.1700
Data Index: 7525799 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.7789. Min Act: -0.1700
Data Index: 2918182 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.7476. Min Act: -0.1700
Data Index: 1216738 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.6851. Min Act: -0.1700
Data Index: 8800561 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.6851. Min Act: -0.1700
Data Index: 5019439 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.6539. Min Act: -0.1700
Data Index: 5633810 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.6226. Min Act: -0.1700
Data Index: 7030859 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.6539. Min Act: -0.1700
Data Index: 5009542 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.6539. Min Act: -0.1700
Data Index: 6287080 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.6539. Min Act: -0.1700
Data Index: 7019231 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.6226. Min Act: -0.1700
Data Index: 5060782 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.5914. Min Act: -0.1700
Data Index: 3447969 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4039. Min Range: -7.4039
Max Act: 6.5601. Min Act: -0.1700
Data Index: 5953957 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19