Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.8515. Min Act: -0.1700
Data Index: 1742368 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.7890. Min Act: -0.1700
Data Index: 1742364 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.5390. Min Act: -0.1700
Data Index: 4205003 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.2577. Min Act: -0.1700
Data Index: 7706856 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.2265. Min Act: -0.1700
Data Index: 4312380 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.1640. Min Act: -0.1700
Data Index: 7384810 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.0702. Min Act: -0.1700
Data Index: 3678711 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.0702. Min Act: -0.1700
Data Index: 212140 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.0702. Min Act: -0.1700
Data Index: 632707 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.0390. Min Act: -0.1700
Data Index: 152418 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.0390. Min Act: -0.1700
Data Index: 7630545 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.0390. Min Act: -0.1700
Data Index: 8661857 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.0077. Min Act: -0.1700
Data Index: 6473435 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.0077. Min Act: -0.1700
Data Index: 4875959 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8515. Min Range: -6.8515
Max Act: 5.9765. Min Act: -0.1700
Data Index: 2025992 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8515. Min Range: -6.8515
Max Act: 6.0077. Min Act: -0.1700
Data Index: 1144165 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8515. Min Range: -6.8515
Max Act: 5.9765. Min Act: -0.1700
Data Index: 7896541 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8515. Min Range: -6.8515
Max Act: 5.9765. Min Act: -0.1700
Data Index: 1893307 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8515. Min Range: -6.8515
Max Act: 5.9140. Min Act: -0.1700
Data Index: 2592598 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8515. Min Range: -6.8515
Max Act: 5.9452. Min Act: -0.1700
Data Index: 1260098 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19