Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1400. Min Range: -6.1400
Max Act: 6.1400. Min Act: -0.1700
Data Index: 366704 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.6400. Min Act: -0.1700
Data Index: 5779441 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.6087. Min Act: -0.1700
Data Index: 1995779 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.5775. Min Act: -0.1700
Data Index: 882709 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.5462. Min Act: -0.1700
Data Index: 998665 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.5150. Min Act: -0.1700
Data Index: 5512381 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.5150. Min Act: -0.1700
Data Index: 6758299 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.5150. Min Act: -0.1700
Data Index: 826247 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.4837. Min Act: -0.1700
Data Index: 2575155 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.4525. Min Act: -0.1700
Data Index: 2091763 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.3900. Min Act: -0.1700
Data Index: 941335 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.3587. Min Act: -0.1700
Data Index: 4947848 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.3275. Min Act: -0.1700
Data Index: 2415505 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.3587. Min Act: -0.1700
Data Index: 4889708 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.2962. Min Act: -0.1700
Data Index: 8442756 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.2650. Min Act: -0.1700
Data Index: 5650916 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.2650. Min Act: -0.1700
Data Index: 2912963 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.2650. Min Act: -0.1700
Data Index: 6981374 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.2650. Min Act: -0.1700
Data Index: 2577691 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1400. Min Range: -6.1400
Max Act: 5.2337. Min Act: -0.1700
Data Index: 4882338 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19