Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6388 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.5549. Min Act: -0.1700
Data Index: 693855 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.4924. Min Act: -0.1700
Data Index: 3575737 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.5237. Min Act: -0.1700
Data Index: 3678520 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.4612. Min Act: -0.1700
Data Index: 5381541 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.4612. Min Act: -0.1700
Data Index: 8492815 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.4612. Min Act: -0.1700
Data Index: 2758104 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.3987. Min Act: -0.1700
Data Index: 4077120 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.3674. Min Act: -0.1700
Data Index: 3955583 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.3674. Min Act: -0.1700
Data Index: 7146502 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.3049. Min Act: -0.1700
Data Index: 381553 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.3049. Min Act: -0.1700
Data Index: 8234399 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.2737. Min Act: -0.1700
Data Index: 3013924 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.2737. Min Act: -0.1700
Data Index: 1062544 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.2424. Min Act: -0.1700
Data Index: 4044261 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.2424. Min Act: -0.1700
Data Index: 3678519 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.2424. Min Act: -0.1700
Data Index: 1430340 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.2424. Min Act: -0.1700
Data Index: 109954 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.2112. Min Act: -0.1700
Data Index: 6213313 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.2112. Min Act: -0.1700
Data Index: 2335526 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5549. Min Range: -6.5549
Max Act: 6.1799. Min Act: -0.1700
Data Index: 7581914 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19