Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 869 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.9869. Min Act: -0.1700
Data Index: 1790255 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.9244. Min Act: -0.1700
Data Index: 5983264 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.9244. Min Act: -0.1700
Data Index: 8634685 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.9244. Min Act: -0.1700
Data Index: 53638 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8932. Min Act: -0.1700
Data Index: 8761681 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8619. Min Act: -0.1700
Data Index: 7945746 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8307. Min Act: -0.1700
Data Index: 4143389 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8619. Min Act: -0.1700
Data Index: 4940245 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8307. Min Act: -0.1700
Data Index: 6531868 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7994. Min Act: -0.1700
Data Index: 7530981 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7994. Min Act: -0.1700
Data Index: 619677 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7994. Min Act: -0.1700
Data Index: 8159882 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7994. Min Act: -0.1700
Data Index: 721765 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7994. Min Act: -0.1700
Data Index: 6878189 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7994. Min Act: -0.1700
Data Index: 6841025 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7682. Min Act: -0.1700
Data Index: 212095 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7682. Min Act: -0.1700
Data Index: 2152667 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7682. Min Act: -0.1700
Data Index: 5993873 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7994. Min Act: -0.1700
Data Index: 6457291 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7682. Min Act: -0.1699
Data Index: 960281 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19