Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3377. Min Range: -6.3377
Max Act: 6.3377. Min Act: -0.1700
Data Index: 579631 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3377. Min Range: -6.3377
Max Act: 6.2752. Min Act: -0.1700
Data Index: 579629 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3377. Min Range: -6.3377
Max Act: 6.1502. Min Act: -0.1672
Data Index: 6515817 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3377. Min Range: -6.3377
Max Act: 6.1189. Min Act: -0.1700
Data Index: 579630 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3377. Min Range: -6.3377
Max Act: 6.1189. Min Act: -0.1700
Data Index: 498295 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3377. Min Range: -6.3377
Max Act: 6.0877. Min Act: -0.1700
Data Index: 4203360 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3377. Min Range: -6.3377
Max Act: 6.0252. Min Act: -0.1700
Data Index: 7628253 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3377. Min Range: -6.3377
Max Act: 6.0252. Min Act: -0.1699
Data Index: 6124889 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3377. Min Range: -6.3377
Max Act: 6.0252. Min Act: -0.1700
Data Index: 4453709 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3377. Min Range: -6.3377
Max Act: 5.9627. Min Act: -0.1700
Data Index: 6632027 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3377. Min Range: -6.3377
Max Act: 5.9627. Min Act: -0.1700
Data Index: 7849781 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3377. Min Range: -6.3377
Max Act: 5.9627. Min Act: -0.1698
Data Index: 8419463 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3377. Min Range: -6.3377
Max Act: 5.9627. Min Act: -0.1690
Data Index: 108768 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3377. Min Range: -6.3377
Max Act: 5.9627. Min Act: -0.1700
Data Index: 8647294 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3377. Min Range: -6.3377
Max Act: 5.9314. Min Act: -0.1700
Data Index: 5364891 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3377. Min Range: -6.3377
Max Act: 5.9314. Min Act: -0.1700
Data Index: 2242863 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3377. Min Range: -6.3377
Max Act: 5.9314. Min Act: -0.1697
Data Index: 5855191 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3377. Min Range: -6.3377
Max Act: 5.9002. Min Act: -0.1700
Data Index: 826776 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3377. Min Range: -6.3377
Max Act: 5.9002. Min Act: -0.1700
Data Index: 6317031 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3377. Min Range: -6.3377
Max Act: 5.9002. Min Act: -0.1657
Data Index: 5694465 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19