Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2335 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1789. Min Range: -7.1789
Max Act: 7.1789. Min Act: -0.1700
Data Index: 6164913 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1789. Min Range: -7.1789
Max Act: 7.0539. Min Act: -0.1700
Data Index: 7405473 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.9914. Min Act: -0.1700
Data Index: 4888370 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.8976. Min Act: -0.1700
Data Index: 6212469 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.8976. Min Act: -0.1700
Data Index: 487280 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.8351. Min Act: -0.1700
Data Index: 6799743 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.8351. Min Act: -0.1700
Data Index: 7746017 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.7414. Min Act: -0.1700
Data Index: 7230955 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.7414. Min Act: -0.1700
Data Index: 6095895 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.7101. Min Act: -0.1700
Data Index: 4347093 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.7101. Min Act: -0.1700
Data Index: 4137221 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.6476. Min Act: -0.1700
Data Index: 3181002 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.6476. Min Act: -0.1700
Data Index: 5583372 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.6476. Min Act: -0.1700
Data Index: 7290661 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.6476. Min Act: -0.1700
Data Index: 8132192 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.6476. Min Act: -0.1700
Data Index: 1626545 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.6476. Min Act: -0.1700
Data Index: 5911362 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.5851. Min Act: -0.1700
Data Index: 259124 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.6164. Min Act: -0.1700
Data Index: 4770704 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1789. Min Range: -7.1789
Max Act: 6.6164. Min Act: -0.1700
Data Index: 4429990 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19