Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2785 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.8273. Min Act: -0.1700
Data Index: 8119540 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.8105. Min Act: -0.1700
Data Index: 68434 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7937. Min Act: -0.1700
Data Index: 8479780 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7770. Min Act: -0.1700
Data Index: 950091 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7770. Min Act: -0.1700
Data Index: 5651662 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7770. Min Act: -0.1700
Data Index: 6092759 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7438. Min Act: -0.1700
Data Index: 5647113 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7273. Min Act: -0.1700
Data Index: 1284140 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7273. Min Act: -0.1700
Data Index: 8586438 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7273. Min Act: -0.1700
Data Index: 5085220 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7109. Min Act: -0.1700
Data Index: 8044123 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7109. Min Act: -0.1700
Data Index: 1924494 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7109. Min Act: -0.1700
Data Index: 5139106 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7273. Min Act: -0.1700
Data Index: 2668930 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7109. Min Act: -0.1700
Data Index: 5651661 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7109. Min Act: -0.1700
Data Index: 1597093 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7109. Min Act: -0.1700
Data Index: 1189591 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7109. Min Act: -0.1700
Data Index: 8002903 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7109. Min Act: -0.1700
Data Index: 2423784 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8273. Min Range: -0.8273
Max Act: 0.7109. Min Act: -0.1700
Data Index: 3125922 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19