Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1008 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3035. Min Range: -7.3035
Max Act: 7.3035. Min Act: -0.1700
Data Index: 5648427 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3035. Min Range: -7.3035
Max Act: 7.2098. Min Act: -0.1699
Data Index: 4064466 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3035. Min Range: -7.3035
Max Act: 7.0223. Min Act: -0.1700
Data Index: 1592052 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.9598. Min Act: -0.1700
Data Index: 6824288 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.8973. Min Act: -0.1700
Data Index: 3158678 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.8660. Min Act: -0.1700
Data Index: 7734449 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.8660. Min Act: -0.1700
Data Index: 7831338 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.8660. Min Act: -0.1700
Data Index: 4753721 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.8348. Min Act: -0.1700
Data Index: 6952140 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.8035. Min Act: -0.1700
Data Index: 2106289 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.8035. Min Act: -0.1700
Data Index: 5363299 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.8660. Min Act: -0.1700
Data Index: 357185 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.8348. Min Act: -0.1700
Data Index: 357183 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.8035. Min Act: -0.1700
Data Index: 4013364 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.7723. Min Act: -0.1700
Data Index: 765651 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.7410. Min Act: -0.1700
Data Index: 357175 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.7723. Min Act: -0.1700
Data Index: 8507478 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.7098. Min Act: -0.1700
Data Index: 3034258 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.6785. Min Act: -0.1700
Data Index: 6459865 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3035. Min Range: -7.3035
Max Act: 6.6785. Min Act: -0.1700
Data Index: 1285003 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19