Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.3668. Min Act: -0.1700
Data Index: 473263 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.3668. Min Act: -0.1700
Data Index: 4983918 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.3043. Min Act: -0.1700
Data Index: 1473001 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.3668. Min Act: -0.1700
Data Index: 3577274 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.3355. Min Act: -0.1700
Data Index: 1380425 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.3355. Min Act: -0.1700
Data Index: 5016767 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.3043. Min Act: -0.1700
Data Index: 473264 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.3043. Min Act: -0.1700
Data Index: 5567217 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.3043. Min Act: -0.1700
Data Index: 4983919 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.3355. Min Act: -0.1700
Data Index: 4788540 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.3043. Min Act: -0.1700
Data Index: 2392122 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.2730. Min Act: -0.1700
Data Index: 4567054 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.2730. Min Act: -0.1700
Data Index: 2112494 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.2730. Min Act: -0.1700
Data Index: 7641779 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.2730. Min Act: -0.1700
Data Index: 267599 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.2730. Min Act: -0.1700
Data Index: 524778 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.2105. Min Act: -0.1700
Data Index: 6942066 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.2418. Min Act: -0.1700
Data Index: 4559484 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.2418. Min Act: -0.1700
Data Index: 7713558 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.2105. Min Act: -0.1700
Data Index: 8741482 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19