Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 246 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.2290. Min Act: -0.1700
Data Index: 2583755 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.2290. Min Act: -0.1700
Data Index: 3599642 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1978. Min Act: -0.1700
Data Index: 7537531 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1665. Min Act: -0.1700
Data Index: 5546624 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1665. Min Act: -0.1700
Data Index: 3075655 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1665. Min Act: -0.1700
Data Index: 8064865 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1353. Min Act: -0.1700
Data Index: 3846727 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1353. Min Act: -0.1700
Data Index: 4749027 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1353. Min Act: -0.1700
Data Index: 286387 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1353. Min Act: -0.1700
Data Index: 185521 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1353. Min Act: -0.1700
Data Index: 2730741 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1040. Min Act: -0.1700
Data Index: 3938979 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.0727. Min Act: -0.1700
Data Index: 4155625 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1040. Min Act: -0.1700
Data Index: 431159 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1040. Min Act: -0.1700
Data Index: 3735089 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1353. Min Act: -0.1700
Data Index: 409019 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1040. Min Act: -0.1700
Data Index: 404177 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1040. Min Act: -0.1700
Data Index: 7119776 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1040. Min Act: -0.1700
Data Index: 276562 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1040. Min Act: -0.1700
Data Index: 1557987 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19