Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3222 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.6202. Min Act: -0.1700
Data Index: 5231392 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.5577. Min Act: -0.1700
Data Index: 1217202 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.5577. Min Act: -0.1700
Data Index: 6431263 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.5265. Min Act: -0.1700
Data Index: 3543911 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.4952. Min Act: -0.1700
Data Index: 7948808 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.4640. Min Act: -0.1700
Data Index: 846001 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.4327. Min Act: -0.1700
Data Index: 116288 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.4015. Min Act: -0.1700
Data Index: 2661205 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.3390. Min Act: -0.1700
Data Index: 1495615 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.3077. Min Act: -0.1700
Data Index: 5639135 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.2452. Min Act: -0.1700
Data Index: 4382634 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.2140. Min Act: -0.1700
Data Index: 1158985 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.1827. Min Act: -0.1700
Data Index: 5706549 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.1827. Min Act: -0.1700
Data Index: 2478299 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.1827. Min Act: -0.1700
Data Index: 5856462 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.1202. Min Act: -0.1700
Data Index: 2720875 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.1515. Min Act: -0.1700
Data Index: 3664915 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.1515. Min Act: -0.1700
Data Index: 5379830 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.0889. Min Act: -0.1700
Data Index: 3132446 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6202. Min Range: -4.6202
Max Act: 4.1515. Min Act: -0.1700
Data Index: 1679978 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19