Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2361 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.8294. Min Act: -0.1700
Data Index: 2047528 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.5794. Min Act: -0.1700
Data Index: 7401225 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.5169. Min Act: -0.1700
Data Index: 2510991 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.5169. Min Act: -0.1700
Data Index: 1095476 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.5169. Min Act: -0.1700
Data Index: 6138810 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.4544. Min Act: -0.1700
Data Index: 4841510 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.3607. Min Act: -0.1700
Data Index: 7749040 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.3607. Min Act: -0.1700
Data Index: 8354567 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.3607. Min Act: -0.1700
Data Index: 3133998 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.2982. Min Act: -0.1700
Data Index: 6507461 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.2669. Min Act: -0.1700
Data Index: 1245549 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.2044. Min Act: -0.1700
Data Index: 3966628 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.2044. Min Act: -0.1700
Data Index: 1786778 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.2044. Min Act: -0.1700
Data Index: 8447760 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.1732. Min Act: -0.1700
Data Index: 483220 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.1732. Min Act: -0.1700
Data Index: 1484414 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.1732. Min Act: -0.1700
Data Index: 3455908 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.1732. Min Act: -0.1700
Data Index: 2541907 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.1732. Min Act: -0.1700
Data Index: 6521666 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.1732. Min Act: -0.1700
Data Index: 6526453 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19