Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0057. Min Range: -7.0057
Max Act: 7.0057. Min Act: -0.1700
Data Index: 4507275 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.7557. Min Act: -0.1700
Data Index: 1245211 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.5995. Min Act: -0.1700
Data Index: 6107441 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.5682. Min Act: -0.1700
Data Index: 5013798 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.5682. Min Act: -0.1700
Data Index: 3021498 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.5682. Min Act: -0.1700
Data Index: 3648836 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.5370. Min Act: -0.1700
Data Index: 2881538 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.5370. Min Act: -0.1700
Data Index: 7141317 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.5057. Min Act: -0.1700
Data Index: 569945 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.5057. Min Act: -0.1700
Data Index: 3321013 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.4745. Min Act: -0.1700
Data Index: 6034644 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.4745. Min Act: -0.1700
Data Index: 5199048 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.4745. Min Act: -0.1700
Data Index: 944338 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.4432. Min Act: -0.1700
Data Index: 4388514 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.4432. Min Act: -0.1700
Data Index: 3990787 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.4432. Min Act: -0.1700
Data Index: 4074673 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.4432. Min Act: -0.1700
Data Index: 5199052 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.4432. Min Act: -0.1700
Data Index: 5845103 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.4120. Min Act: -0.1700
Data Index: 7128368 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0057. Min Range: -7.0057
Max Act: 6.3807. Min Act: -0.1700
Data Index: 5199051 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19