Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4293 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.6751. Min Act: -0.1700
Data Index: 69049 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.6751. Min Act: -0.1700
Data Index: 4494851 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.6439. Min Act: -0.1700
Data Index: 799353 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.6126. Min Act: -0.1700
Data Index: 8776245 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.6126. Min Act: -0.1700
Data Index: 1751116 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.5814. Min Act: -0.1700
Data Index: 5956098 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.5501. Min Act: -0.1700
Data Index: 8633954 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.5501. Min Act: -0.1700
Data Index: 7556457 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.4876. Min Act: -0.1700
Data Index: 6388120 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.4876. Min Act: -0.1700
Data Index: 1724176 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.4876. Min Act: -0.1700
Data Index: 6093913 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.4876. Min Act: -0.1700
Data Index: 3147717 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.4564. Min Act: -0.1700
Data Index: 4659201 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.4876. Min Act: -0.1700
Data Index: 3656528 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.4564. Min Act: -0.1700
Data Index: 2005538 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.4564. Min Act: -0.1700
Data Index: 3143155 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.4251. Min Act: -0.1700
Data Index: 5762150 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.4564. Min Act: -0.1700
Data Index: 5040381 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.4564. Min Act: -0.1700
Data Index: 6450752 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6751. Min Range: -4.6751
Max Act: 4.4251. Min Act: -0.1700
Data Index: 2971507 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19