Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5173 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.6807. Min Act: -0.1700
Data Index: 2365938 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.4932. Min Act: -0.1700
Data Index: 1353599 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.4620. Min Act: -0.1700
Data Index: 7540446 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.3995. Min Act: -0.1700
Data Index: 6226240 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.2745. Min Act: -0.1700
Data Index: 6788729 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.2120. Min Act: -0.1700
Data Index: 5380595 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.2120. Min Act: -0.1700
Data Index: 5154816 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.2432. Min Act: -0.1700
Data Index: 142178 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.2120. Min Act: -0.1700
Data Index: 7682096 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.2120. Min Act: -0.1700
Data Index: 5848318 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.1807. Min Act: -0.1700
Data Index: 811687 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.1182. Min Act: -0.1700
Data Index: 7430343 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.1494. Min Act: -0.1700
Data Index: 5030767 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.0869. Min Act: -0.1700
Data Index: 5896044 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.0869. Min Act: -0.1700
Data Index: 5525 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.0869. Min Act: -0.1700
Data Index: 2099435 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.1182. Min Act: -0.1700
Data Index: 4934641 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.0557. Min Act: -0.1700
Data Index: 3886175 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.0557. Min Act: -0.1700
Data Index: 4661995 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.0557. Min Act: -0.1700
Data Index: 8744775 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19