Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4829 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.6769. Min Act: -0.1700
Data Index: 6544334 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.5519. Min Act: -0.1700
Data Index: 3549596 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.4894. Min Act: -0.1700
Data Index: 5056715 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.4269. Min Act: -0.1700
Data Index: 671650 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.3957. Min Act: -0.1700
Data Index: 7204640 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.3957. Min Act: -0.1700
Data Index: 7113056 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.3957. Min Act: -0.1700
Data Index: 7564443 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.3957. Min Act: -0.1700
Data Index: 485581 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.3332. Min Act: -0.1700
Data Index: 6685136 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.3332. Min Act: -0.1700
Data Index: 8495235 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.3019. Min Act: -0.1700
Data Index: 5188243 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.3019. Min Act: -0.1700
Data Index: 1224025 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.3019. Min Act: -0.1700
Data Index: 562307 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.2394. Min Act: -0.1700
Data Index: 7656118 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.2707. Min Act: -0.1700
Data Index: 7740475 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.2707. Min Act: -0.1700
Data Index: 6017327 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.2707. Min Act: -0.1700
Data Index: 4909565 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.2394. Min Act: -0.1700
Data Index: 605140 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.2082. Min Act: -0.1700
Data Index: 1241473 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6769. Min Range: -6.6769
Max Act: 6.2082. Min Act: -0.1700
Data Index: 2431473 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19