Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3741 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.5034. Min Act: -0.1700
Data Index: 2191120 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.5034. Min Act: -0.1700
Data Index: 574798 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.4721. Min Act: -0.1700
Data Index: 6756507 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.4721. Min Act: -0.1700
Data Index: 699179 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.4096. Min Act: -0.1700
Data Index: 7746195 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.4409. Min Act: -0.1700
Data Index: 4999335 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.3784. Min Act: -0.1700
Data Index: 1182359 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.3784. Min Act: -0.1700
Data Index: 8126807 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.3784. Min Act: -0.1700
Data Index: 8275655 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.3784. Min Act: -0.1700
Data Index: 4320557 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.3784. Min Act: -0.1700
Data Index: 4471185 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.3784. Min Act: -0.1700
Data Index: 3539937 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.3471. Min Act: -0.1700
Data Index: 6002988 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.3471. Min Act: -0.1700
Data Index: 911924 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.3471. Min Act: -0.1700
Data Index: 3258777 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.3159. Min Act: -0.1700
Data Index: 3246780 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.3471. Min Act: -0.1700
Data Index: 4358103 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.3471. Min Act: -0.1700
Data Index: 7751953 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.3159. Min Act: -0.1700
Data Index: 3350655 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5034. Min Range: -6.5034
Max Act: 6.3471. Min Act: -0.1700
Data Index: 8123404 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19