Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5127 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.5899. Min Act: -0.1700
Data Index: 8401038 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.5586. Min Act: -0.1700
Data Index: 8823126 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.5274. Min Act: -0.1700
Data Index: 6582872 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.5274. Min Act: -0.1700
Data Index: 5587530 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.4649. Min Act: -0.1700
Data Index: 3879110 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.4649. Min Act: -0.1700
Data Index: 4499534 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.4649. Min Act: -0.1700
Data Index: 7103247 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.4024. Min Act: -0.1700
Data Index: 2663544 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.3711. Min Act: -0.1700
Data Index: 7345940 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.3711. Min Act: -0.1700
Data Index: 5549161 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.3711. Min Act: -0.1700
Data Index: 1506458 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.3711. Min Act: -0.1700
Data Index: 6437348 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.3399. Min Act: -0.1700
Data Index: 2515000 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.3711. Min Act: -0.1700
Data Index: 2191856 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.3399. Min Act: -0.1700
Data Index: 2358629 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.3399. Min Act: -0.1700
Data Index: 1963396 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.2774. Min Act: -0.1700
Data Index: 3770806 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.3399. Min Act: -0.1700
Data Index: 595068 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.3086. Min Act: -0.1700
Data Index: 7314110 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5899. Min Range: -5.5899
Max Act: 5.3086. Min Act: -0.1700
Data Index: 4161045 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19