Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3713 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3150. Min Range: -6.3150
Max Act: 6.3150. Min Act: -0.1700
Data Index: 8189863 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3150. Min Range: -6.3150
Max Act: 6.0962. Min Act: -0.1700
Data Index: 5752789 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3150. Min Range: -6.3150
Max Act: 6.0025. Min Act: -0.1700
Data Index: 1227074 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.8775. Min Act: -0.1700
Data Index: 1120919 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.8150. Min Act: -0.1700
Data Index: 7257641 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.7837. Min Act: -0.1700
Data Index: 8204777 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.7525. Min Act: -0.1700
Data Index: 8657919 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.7212. Min Act: -0.1700
Data Index: 1525903 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.6900. Min Act: -0.1700
Data Index: 8558916 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.6275. Min Act: -0.1700
Data Index: 8797175 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.6587. Min Act: -0.1700
Data Index: 6435477 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.6587. Min Act: -0.1700
Data Index: 5367223 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.6587. Min Act: -0.1700
Data Index: 7362136 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.6275. Min Act: -0.1700
Data Index: 7950017 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.6275. Min Act: -0.1700
Data Index: 5081377 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.6275. Min Act: -0.1700
Data Index: 6431164 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.5962. Min Act: -0.1700
Data Index: 2881606 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.6275. Min Act: -0.1700
Data Index: 648295 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.5962. Min Act: -0.1700
Data Index: 7905023 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3150. Min Range: -6.3150
Max Act: 5.5650. Min Act: -0.1700
Data Index: 4744189 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19