Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2037 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.7709. Min Act: -0.1700
Data Index: 6625794 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.7709. Min Act: -0.1700
Data Index: 120502 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.7363. Min Act: -0.1700
Data Index: 5129636 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.7190. Min Act: -0.1700
Data Index: 2857333 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.7190. Min Act: -0.1700
Data Index: 6982279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.7190. Min Act: -0.1700
Data Index: 5042036 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.7017. Min Act: -0.1700
Data Index: 2963068 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.6844. Min Act: -0.1700
Data Index: 1071137 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.7017. Min Act: -0.1700
Data Index: 3040608 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.6844. Min Act: -0.1700
Data Index: 5925949 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.6844. Min Act: -0.1700
Data Index: 16269 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.7017. Min Act: -0.1700
Data Index: 3046039 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.7017. Min Act: -0.1700
Data Index: 6431288 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.6670. Min Act: -0.1700
Data Index: 1574743 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.6670. Min Act: -0.1700
Data Index: 6372608 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.6670. Min Act: -0.1700
Data Index: 3528615 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.6322. Min Act: -0.1700
Data Index: 4538453 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.6322. Min Act: -0.1700
Data Index: 4736812 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.6496. Min Act: -0.1700
Data Index: 4626322 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7709. Min Range: -1.7709
Max Act: 1.6496. Min Act: -0.1700
Data Index: 409445 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19