Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.7410. Min Act: -0.1700
Data Index: 4601941 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.5535. Min Act: -0.1700
Data Index: 2186587 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.4285. Min Act: -0.1700
Data Index: 7227186 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.4285. Min Act: -0.1700
Data Index: 2186588 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.4910. Min Act: -0.1700
Data Index: 8584192 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.4285. Min Act: -0.1700
Data Index: 8561908 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.4285. Min Act: -0.1700
Data Index: 7582462 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.4285. Min Act: -0.1700
Data Index: 3090255 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.4285. Min Act: -0.1700
Data Index: 248994 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.4285. Min Act: -0.1700
Data Index: 4601939 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.3660. Min Act: -0.1700
Data Index: 1051262 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.3660. Min Act: -0.1700
Data Index: 248993 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.3035. Min Act: -0.1700
Data Index: 8584193 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.3660. Min Act: -0.1700
Data Index: 6351321 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.3035. Min Act: -0.1700
Data Index: 7227187 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.2723. Min Act: -0.1700
Data Index: 6351322 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.2723. Min Act: -0.1700
Data Index: 5553786 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.2410. Min Act: -0.1700
Data Index: 8561907 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.2098. Min Act: -0.1700
Data Index: 225152 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7410. Min Range: -8.7410
Max Act: 8.1160. Min Act: -0.1700
Data Index: 7533300 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19