Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5713 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.9542. Min Act: -0.1700
Data Index: 126002 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.5479. Min Act: -0.1700
Data Index: 996041 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.3917. Min Act: -0.1700
Data Index: 2533682 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.2042. Min Act: -0.1700
Data Index: 1453486 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.1417. Min Act: -0.1700
Data Index: 7763375 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.1104. Min Act: -0.1700
Data Index: 3167927 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.0792. Min Act: -0.1700
Data Index: 7897412 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.0792. Min Act: -0.1700
Data Index: 6089801 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.0792. Min Act: -0.1700
Data Index: 1129128 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.0792. Min Act: -0.1700
Data Index: 965781 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.0167. Min Act: -0.1700
Data Index: 5496728 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.0167. Min Act: -0.1700
Data Index: 6377975 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.0167. Min Act: -0.1700
Data Index: 7060986 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9542. Min Range: -6.9542
Max Act: 5.9854. Min Act: -0.1700
Data Index: 7192066 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9542. Min Range: -6.9542
Max Act: 5.9854. Min Act: -0.1700
Data Index: 5021521 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9542. Min Range: -6.9542
Max Act: 5.9854. Min Act: -0.1700
Data Index: 6306135 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9542. Min Range: -6.9542
Max Act: 5.9854. Min Act: -0.1700
Data Index: 63606 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9542. Min Range: -6.9542
Max Act: 5.9542. Min Act: -0.1700
Data Index: 3207608 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9542. Min Range: -6.9542
Max Act: 5.9542. Min Act: -0.1700
Data Index: 1484742 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9542. Min Range: -6.9542
Max Act: 5.9542. Min Act: -0.1700
Data Index: 4439757 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19