Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2693. Min Range: -8.2693
Max Act: 8.2693. Min Act: -0.1700
Data Index: 3595497 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.9256. Min Act: -0.1700
Data Index: 4569667 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.8006. Min Act: -0.1700
Data Index: 1612441 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.7381. Min Act: -0.1700
Data Index: 8349002 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.7693. Min Act: -0.1700
Data Index: 6082439 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.6756. Min Act: -0.1700
Data Index: 8208832 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.6443. Min Act: -0.1700
Data Index: 7079057 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.6443. Min Act: -0.1700
Data Index: 6553697 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.5818. Min Act: -0.1700
Data Index: 3929920 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.6131. Min Act: -0.1700
Data Index: 4938768 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.4568. Min Act: -0.1700
Data Index: 8672079 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.4881. Min Act: -0.1700
Data Index: 912360 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.4881. Min Act: -0.1700
Data Index: 2667911 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.5193. Min Act: -0.1700
Data Index: 1569975 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.4568. Min Act: -0.1700
Data Index: 5887910 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.4568. Min Act: -0.1700
Data Index: 4620045 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.4568. Min Act: -0.1700
Data Index: 7265178 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.3943. Min Act: -0.1700
Data Index: 8625670 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.4256. Min Act: -0.1700
Data Index: 2015993 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2693. Min Range: -8.2693
Max Act: 7.4256. Min Act: -0.1700
Data Index: 4326841 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19