Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4383 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4477. Min Range: -4.4477
Max Act: 4.4477. Min Act: -0.1700
Data Index: 2925569 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4477. Min Range: -4.4477
Max Act: 4.1977. Min Act: -0.1700
Data Index: 1836020 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4477. Min Range: -4.4477
Max Act: 4.2289. Min Act: -0.1700
Data Index: 3585716 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4477. Min Range: -4.4477
Max Act: 4.1352. Min Act: -0.1700
Data Index: 2865930 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4477. Min Range: -4.4477
Max Act: 4.0726. Min Act: -0.1700
Data Index: 7267152 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4477. Min Range: -4.4477
Max Act: 4.0414. Min Act: -0.1700
Data Index: 7641324 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4477. Min Range: -4.4477
Max Act: 4.0414. Min Act: -0.1700
Data Index: 4126486 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4477. Min Range: -4.4477
Max Act: 4.0414. Min Act: -0.1700
Data Index: 8306847 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4477. Min Range: -4.4477
Max Act: 4.0101. Min Act: -0.1700
Data Index: 1620691 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4477. Min Range: -4.4477
Max Act: 3.9789. Min Act: -0.1700
Data Index: 3841656 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4477. Min Range: -4.4477
Max Act: 3.9789. Min Act: -0.1700
Data Index: 6048567 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4477. Min Range: -4.4477
Max Act: 3.9476. Min Act: -0.1700
Data Index: 8167772 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4477. Min Range: -4.4477
Max Act: 3.9789. Min Act: -0.1700
Data Index: 3247656 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4477. Min Range: -4.4477
Max Act: 3.9476. Min Act: -0.1700
Data Index: 2660804 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4477. Min Range: -4.4477
Max Act: 3.9476. Min Act: -0.1700
Data Index: 4590842 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4477. Min Range: -4.4477
Max Act: 3.9476. Min Act: -0.1700
Data Index: 7647936 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4477. Min Range: -4.4477
Max Act: 3.9476. Min Act: -0.1700
Data Index: 8672057 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4477. Min Range: -4.4477
Max Act: 3.9476. Min Act: -0.1700
Data Index: 6615534 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4477. Min Range: -4.4477
Max Act: 3.9476. Min Act: -0.1700
Data Index: 6089422 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4477. Min Range: -4.4477
Max Act: 3.9163. Min Act: -0.1700
Data Index: 202710 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19