Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1075 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.7637. Min Act: -0.1700
Data Index: 724895 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.7012. Min Act: -0.1700
Data Index: 6269924 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.7012. Min Act: -0.1700
Data Index: 3251393 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.7012. Min Act: -0.1700
Data Index: 863124 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.6699. Min Act: -0.1700
Data Index: 828576 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.6387. Min Act: -0.1700
Data Index: 6944518 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.6387. Min Act: -0.1700
Data Index: 2109240 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.5762. Min Act: -0.1700
Data Index: 3483989 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.5762. Min Act: -0.1700
Data Index: 7597624 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.5449. Min Act: -0.1700
Data Index: 5683128 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.5137. Min Act: -0.1700
Data Index: 2686504 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.5137. Min Act: -0.1700
Data Index: 5446054 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.4824. Min Act: -0.1700
Data Index: 280096 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.4824. Min Act: -0.1700
Data Index: 6554439 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.4824. Min Act: -0.1700
Data Index: 2114577 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.4512. Min Act: -0.1700
Data Index: 2710721 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.4824. Min Act: -0.1700
Data Index: 5196800 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.4512. Min Act: -0.1700
Data Index: 6904484 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.4512. Min Act: -0.1700
Data Index: 533603 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7637. Min Range: -5.7637
Max Act: 5.4512. Min Act: -0.1700
Data Index: 4905423 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19