Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4675 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0765. Min Range: -8.0765
Max Act: 8.0452. Min Act: -0.1700
Data Index: 5659091 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0765. Min Range: -8.0765
Max Act: 8.0140. Min Act: -0.1700
Data Index: 2278390 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0765. Min Range: -8.0765
Max Act: 8.0765. Min Act: -0.1700
Data Index: 5308272 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.9827. Min Act: -0.1700
Data Index: 2648023 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.9202. Min Act: -0.1700
Data Index: 6988625 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.8577. Min Act: -0.1700
Data Index: 1439840 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.8577. Min Act: -0.1700
Data Index: 7227531 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.8577. Min Act: -0.1700
Data Index: 3424863 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.8265. Min Act: -0.1700
Data Index: 4115708 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.7952. Min Act: -0.1700
Data Index: 8732340 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.7640. Min Act: -0.1700
Data Index: 1311538 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.7015. Min Act: -0.1700
Data Index: 8023684 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.7015. Min Act: -0.1700
Data Index: 6827543 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.6702. Min Act: -0.1700
Data Index: 6751888 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.6702. Min Act: -0.1700
Data Index: 4736984 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.6702. Min Act: -0.1700
Data Index: 6570517 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.6077. Min Act: -0.1700
Data Index: 8700227 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.6390. Min Act: -0.1700
Data Index: 4527179 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.5765. Min Act: -0.1700
Data Index: 763501 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0765. Min Range: -8.0765
Max Act: 7.6077. Min Act: -0.1700
Data Index: 2001829 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19