Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5880 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.8782. Min Act: -0.1700
Data Index: 5665468 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.7219. Min Act: -0.1700
Data Index: 2881013 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.7219. Min Act: -0.1700
Data Index: 6089666 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.6282. Min Act: -0.1700
Data Index: 1741122 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.5969. Min Act: -0.1700
Data Index: 731112 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.5657. Min Act: -0.1700
Data Index: 3185564 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.5657. Min Act: -0.1700
Data Index: 7745511 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.5657. Min Act: -0.1700
Data Index: 8110337 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.4719. Min Act: -0.1700
Data Index: 1879565 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.4407. Min Act: -0.1700
Data Index: 8549068 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.3782. Min Act: -0.1700
Data Index: 659331 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.4407. Min Act: -0.1700
Data Index: 99533 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.3782. Min Act: -0.1700
Data Index: 8654669 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.4407. Min Act: -0.1700
Data Index: 8648333 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.3782. Min Act: -0.1700
Data Index: 8618269 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.3469. Min Act: -0.1700
Data Index: 4883022 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.3469. Min Act: -0.1700
Data Index: 3579649 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.3469. Min Act: -0.1700
Data Index: 6264835 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.3469. Min Act: -0.1700
Data Index: 1163515 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8782. Min Range: -6.8782
Max Act: 6.3157. Min Act: -0.1700
Data Index: 1591515 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19