Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2992 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.9680. Min Act: -0.1700
Data Index: 292593 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.9367. Min Act: -0.1700
Data Index: 2871532 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.8430. Min Act: -0.1700
Data Index: 3594755 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.8430. Min Act: -0.1700
Data Index: 6226235 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.8430. Min Act: -0.1700
Data Index: 2692272 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.8117. Min Act: -0.1700
Data Index: 780820 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.7805. Min Act: -0.1700
Data Index: 6049673 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.7805. Min Act: -0.1700
Data Index: 1851030 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.7805. Min Act: -0.1700
Data Index: 2682341 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.7492. Min Act: -0.1700
Data Index: 2522498 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.7492. Min Act: -0.1700
Data Index: 336710 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.7492. Min Act: -0.1700
Data Index: 2107354 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.7492. Min Act: -0.1700
Data Index: 6074561 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.7180. Min Act: -0.1700
Data Index: 8620429 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.7180. Min Act: -0.1700
Data Index: 8312239 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.7180. Min Act: -0.1700
Data Index: 5194561 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.7180. Min Act: -0.1700
Data Index: 857110 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.6555. Min Act: -0.1700
Data Index: 753486 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.6867. Min Act: -0.1700
Data Index: 2399682 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9680. Min Range: -4.9680
Max Act: 4.6867. Min Act: -0.1700
Data Index: 1695576 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19