Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3461 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.5180. Min Act: -0.1700
Data Index: 4820364 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.4555. Min Act: -0.1700
Data Index: 3003749 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.4555. Min Act: -0.1700
Data Index: 8084433 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.4242. Min Act: -0.1700
Data Index: 44120 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.4555. Min Act: -0.1700
Data Index: 6224907 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.3930. Min Act: -0.1700
Data Index: 2513716 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.3930. Min Act: -0.1700
Data Index: 6106066 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.3617. Min Act: -0.1700
Data Index: 2344530 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.2992. Min Act: -0.1700
Data Index: 8540228 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.2992. Min Act: -0.1700
Data Index: 2344531 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.2992. Min Act: -0.1700
Data Index: 3072227 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.2680. Min Act: -0.1700
Data Index: 3111377 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.2680. Min Act: -0.1700
Data Index: 152947 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.2055. Min Act: -0.1700
Data Index: 6224908 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.2367. Min Act: -0.1700
Data Index: 8577214 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.2367. Min Act: -0.1700
Data Index: 8145631 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.2055. Min Act: -0.1669
Data Index: 5200947 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.1742. Min Act: -0.1700
Data Index: 7722400 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.1742. Min Act: -0.1700
Data Index: 2782561 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.2055. Min Act: -0.1700
Data Index: 8459051 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19