Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3265 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.9821. Min Act: -0.1700
Data Index: 4875214 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.9509. Min Act: -0.1700
Data Index: 6302075 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.8884. Min Act: -0.1700
Data Index: 5324235 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.8259. Min Act: -0.1700
Data Index: 792594 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.7946. Min Act: -0.1700
Data Index: 1060873 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.7634. Min Act: -0.1700
Data Index: 7814096 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.7634. Min Act: -0.1700
Data Index: 8732490 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.7321. Min Act: -0.1700
Data Index: 8425144 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.7634. Min Act: -0.1700
Data Index: 1519551 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.7321. Min Act: -0.1700
Data Index: 3822899 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.7009. Min Act: -0.1700
Data Index: 8354336 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.7009. Min Act: -0.1700
Data Index: 8344240 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.7009. Min Act: -0.1700
Data Index: 8089994 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.6696. Min Act: -0.1700
Data Index: 7453687 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.6384. Min Act: -0.1700
Data Index: 3423936 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.6384. Min Act: -0.1700
Data Index: 6220640 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.6384. Min Act: -0.1700
Data Index: 1783844 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.6384. Min Act: -0.1700
Data Index: 92797 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.6384. Min Act: -0.1700
Data Index: 7637709 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9821. Min Range: -4.9821
Max Act: 4.6384. Min Act: -0.1700
Data Index: 7764075 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19