Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5747 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1315. Min Range: -4.1315
Max Act: 4.1315. Min Act: -0.1700
Data Index: 1751395 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.9440. Min Act: -0.1700
Data Index: 8308921 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.9440. Min Act: -0.1700
Data Index: 3858438 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.8814. Min Act: -0.1700
Data Index: 4857688 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.8189. Min Act: -0.1700
Data Index: 7985820 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.7876. Min Act: -0.1700
Data Index: 2438667 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.8032. Min Act: -0.1700
Data Index: 4070001 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.7563. Min Act: -0.1700
Data Index: 4640974 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.7563. Min Act: -0.1700
Data Index: 6882097 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.7250. Min Act: -0.1700
Data Index: 5924720 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.7094. Min Act: -0.1700
Data Index: 3542262 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.6781. Min Act: -0.1700
Data Index: 956826 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.7094. Min Act: -0.1700
Data Index: 8088413 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.7250. Min Act: -0.1700
Data Index: 8135762 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.6938. Min Act: -0.1700
Data Index: 7217839 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.6781. Min Act: -0.1700
Data Index: 3422579 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.6781. Min Act: -0.1700
Data Index: 4676927 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.6625. Min Act: -0.1700
Data Index: 3422580 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.6468. Min Act: -0.1700
Data Index: 564812 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1315. Min Range: -4.1315
Max Act: 3.6468. Min Act: -0.1700
Data Index: 7446672 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19