Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 888 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0169. Min Range: -5.0169
Max Act: 5.0169. Min Act: -0.1700
Data Index: 5791669 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.9857. Min Act: -0.1700
Data Index: 1237962 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.9857. Min Act: -0.1700
Data Index: 6377317 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.9857. Min Act: -0.1700
Data Index: 238034 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.9857. Min Act: -0.1700
Data Index: 7293827 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.9544. Min Act: -0.1700
Data Index: 4420509 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.9544. Min Act: -0.1700
Data Index: 4011552 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.9857. Min Act: -0.1700
Data Index: 6933628 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.9232. Min Act: -0.1700
Data Index: 5879280 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.9232. Min Act: -0.1700
Data Index: 4689693 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.9232. Min Act: -0.1700
Data Index: 2420795 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.8919. Min Act: -0.1700
Data Index: 2593107 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.8919. Min Act: -0.1700
Data Index: 5032458 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.8919. Min Act: -0.1700
Data Index: 853913 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.8919. Min Act: -0.1700
Data Index: 691411 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.9232. Min Act: -0.1700
Data Index: 3483793 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.9232. Min Act: -0.1700
Data Index: 7470128 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.8607. Min Act: -0.1700
Data Index: 1906933 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.8607. Min Act: -0.1700
Data Index: 586655 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0169. Min Range: -5.0169
Max Act: 4.8607. Min Act: -0.1700
Data Index: 5371714 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19