Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2889 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0446. Min Range: -7.0446
Max Act: 7.0446. Min Act: -0.1700
Data Index: 6628636 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0446. Min Range: -7.0446
Max Act: 6.1071. Min Act: -0.1700
Data Index: 2551336 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0446. Min Range: -7.0446
Max Act: 6.1071. Min Act: -0.1700
Data Index: 5093739 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0446. Min Range: -7.0446
Max Act: 6.0759. Min Act: -0.1700
Data Index: 8726528 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0446. Min Range: -7.0446
Max Act: 6.0759. Min Act: -0.1700
Data Index: 8480874 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0446. Min Range: -7.0446
Max Act: 6.0759. Min Act: -0.1700
Data Index: 3570248 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0446. Min Range: -7.0446
Max Act: 6.0446. Min Act: -0.1700
Data Index: 4705135 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0446. Min Range: -7.0446
Max Act: 5.9821. Min Act: -0.1700
Data Index: 3188678 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0446. Min Range: -7.0446
Max Act: 5.9821. Min Act: -0.1700
Data Index: 7333051 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0446. Min Range: -7.0446
Max Act: 5.9821. Min Act: -0.1700
Data Index: 4267155 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0446. Min Range: -7.0446
Max Act: 5.9509. Min Act: -0.1700
Data Index: 2576822 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0446. Min Range: -7.0446
Max Act: 5.9509. Min Act: -0.1700
Data Index: 2927831 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0446. Min Range: -7.0446
Max Act: 5.9196. Min Act: -0.1700
Data Index: 5783115 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0446. Min Range: -7.0446
Max Act: 5.9196. Min Act: -0.1700
Data Index: 3336896 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0446. Min Range: -7.0446
Max Act: 5.9196. Min Act: -0.1700
Data Index: 4721115 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0446. Min Range: -7.0446
Max Act: 5.8884. Min Act: -0.1700
Data Index: 2737421 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0446. Min Range: -7.0446
Max Act: 5.8884. Min Act: -0.1700
Data Index: 8065004 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0446. Min Range: -7.0446
Max Act: 5.8884. Min Act: -0.1700
Data Index: 6325619 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0446. Min Range: -7.0446
Max Act: 5.8571. Min Act: -0.1700
Data Index: 5513408 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0446. Min Range: -7.0446
Max Act: 5.8259. Min Act: -0.1700
Data Index: 321198 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19