Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2070 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3126. Min Range: -6.3126
Max Act: 6.3126. Min Act: -0.1700
Data Index: 7717530 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3126. Min Range: -6.3126
Max Act: 6.2814. Min Act: -0.1700
Data Index: 6253401 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3126. Min Range: -6.3126
Max Act: 6.2501. Min Act: -0.1700
Data Index: 1295988 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3126. Min Range: -6.3126
Max Act: 6.1564. Min Act: -0.1700
Data Index: 4454020 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3126. Min Range: -6.3126
Max Act: 6.0939. Min Act: -0.1700
Data Index: 6497560 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3126. Min Range: -6.3126
Max Act: 6.0626. Min Act: -0.1700
Data Index: 6159704 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3126. Min Range: -6.3126
Max Act: 6.0626. Min Act: -0.1700
Data Index: 420678 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3126. Min Range: -6.3126
Max Act: 6.0314. Min Act: -0.1700
Data Index: 5426345 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3126. Min Range: -6.3126
Max Act: 6.0314. Min Act: -0.1700
Data Index: 245613 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3126. Min Range: -6.3126
Max Act: 6.0314. Min Act: -0.1700
Data Index: 6968754 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3126. Min Range: -6.3126
Max Act: 6.0001. Min Act: -0.1700
Data Index: 4335106 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3126. Min Range: -6.3126
Max Act: 5.9689. Min Act: -0.1700
Data Index: 5932197 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3126. Min Range: -6.3126
Max Act: 5.9689. Min Act: -0.1700
Data Index: 8638105 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3126. Min Range: -6.3126
Max Act: 5.9064. Min Act: -0.1700
Data Index: 5577091 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3126. Min Range: -6.3126
Max Act: 5.9064. Min Act: -0.1700
Data Index: 91247 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3126. Min Range: -6.3126
Max Act: 5.9064. Min Act: -0.1700
Data Index: 2434756 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3126. Min Range: -6.3126
Max Act: 5.9064. Min Act: -0.1700
Data Index: 7135069 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3126. Min Range: -6.3126
Max Act: 5.8751. Min Act: -0.1700
Data Index: 1878127 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3126. Min Range: -6.3126
Max Act: 5.8751. Min Act: -0.1700
Data Index: 5721674 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3126. Min Range: -6.3126
Max Act: 5.8751. Min Act: -0.1700
Data Index: 258 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19