Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5003 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.5600. Min Act: -0.1700
Data Index: 4884012 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.3413. Min Act: -0.1700
Data Index: 2562998 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.3100. Min Act: -0.1700
Data Index: 3194495 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.2788. Min Act: -0.1700
Data Index: 8775184 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.2788. Min Act: -0.1700
Data Index: 4432143 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.2788. Min Act: -0.1700
Data Index: 3453779 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.2475. Min Act: -0.1700
Data Index: 4994242 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.2163. Min Act: -0.1700
Data Index: 4984640 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.1850. Min Act: -0.1700
Data Index: 6111207 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.1850. Min Act: -0.1700
Data Index: 6635807 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.1850. Min Act: -0.1700
Data Index: 6863879 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.1538. Min Act: -0.1700
Data Index: 7131995 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.1538. Min Act: -0.1700
Data Index: 4884025 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.0913. Min Act: -0.1700
Data Index: 3803074 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.1225. Min Act: -0.1700
Data Index: 1066971 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.1225. Min Act: -0.1700
Data Index: 5073431 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.1225. Min Act: -0.1700
Data Index: 4404686 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.0913. Min Act: -0.1700
Data Index: 7573502 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.1225. Min Act: -0.1700
Data Index: 4443389 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5600. Min Range: -5.5600
Max Act: 5.0600. Min Act: -0.1700
Data Index: 5675306 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19