Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3239 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1485. Min Range: -8.1485
Max Act: 8.1485. Min Act: -0.1700
Data Index: 2359396 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1485. Min Range: -8.1485
Max Act: 8.0235. Min Act: -0.1700
Data Index: 4671714 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.9610. Min Act: -0.1700
Data Index: 7925662 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.8360. Min Act: -0.1700
Data Index: 2533516 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.8360. Min Act: -0.1700
Data Index: 7059126 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.7110. Min Act: -0.1700
Data Index: 4582798 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.7110. Min Act: -0.1700
Data Index: 3606987 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.6485. Min Act: -0.1700
Data Index: 2766251 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.6485. Min Act: -0.1700
Data Index: 6666831 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.5860. Min Act: -0.1700
Data Index: 3155087 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.5860. Min Act: -0.1700
Data Index: 5221757 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.5547. Min Act: -0.1700
Data Index: 1844120 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.5235. Min Act: -0.1700
Data Index: 3951680 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.4922. Min Act: -0.1700
Data Index: 8021686 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.4922. Min Act: -0.1700
Data Index: 809527 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.4922. Min Act: -0.1700
Data Index: 5810287 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.4297. Min Act: -0.1700
Data Index: 5096797 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.4610. Min Act: -0.1700
Data Index: 3500831 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.4297. Min Act: -0.1700
Data Index: 464797 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1485. Min Range: -8.1485
Max Act: 7.3985. Min Act: -0.1700
Data Index: 5977614 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19