Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6395 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.6324. Min Act: -0.1700
Data Index: 71935 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.6012. Min Act: -0.1700
Data Index: 6782147 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.6012. Min Act: -0.1697
Data Index: 710500 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.6012. Min Act: -0.1700
Data Index: 6695621 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.6012. Min Act: -0.1700
Data Index: 4791839 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.6012. Min Act: -0.1700
Data Index: 3167984 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.5699. Min Act: -0.1700
Data Index: 1041389 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.5699. Min Act: -0.1700
Data Index: 5435754 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.5699. Min Act: -0.1697
Data Index: 5367793 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.5699. Min Act: -0.1700
Data Index: 3287564 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.5699. Min Act: -0.1700
Data Index: 3203106 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.5387. Min Act: -0.1700
Data Index: 4877031 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.5387. Min Act: -0.1700
Data Index: 2981605 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.5074. Min Act: -0.1700
Data Index: 6464949 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.5387. Min Act: -0.1700
Data Index: 5693922 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.5387. Min Act: -0.1699
Data Index: 2250398 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.5387. Min Act: -0.1699
Data Index: 7974889 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.5387. Min Act: -0.1700
Data Index: 8089225 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.5387. Min Act: -0.1700
Data Index: 4219809 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6324. Min Range: -5.6324
Max Act: 5.5387. Min Act: -0.1700
Data Index: 1225382 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19