Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3426 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3672. Min Range: -8.3672
Max Act: 8.3672. Min Act: -0.1700
Data Index: 8319358 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3672. Min Range: -8.3672
Max Act: 8.1172. Min Act: -0.1700
Data Index: 2542176 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.9922. Min Act: -0.1700
Data Index: 5774413 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.9922. Min Act: -0.1700
Data Index: 6634791 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.9297. Min Act: -0.1700
Data Index: 2591926 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.8672. Min Act: -0.1700
Data Index: 7853974 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.8672. Min Act: -0.1700
Data Index: 1815066 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.8047. Min Act: -0.1700
Data Index: 3479015 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.7422. Min Act: -0.1700
Data Index: 1586017 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.7422. Min Act: -0.1700
Data Index: 1560320 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.6797. Min Act: -0.1700
Data Index: 1613751 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.6797. Min Act: -0.1700
Data Index: 8333549 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.6797. Min Act: -0.1700
Data Index: 144831 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.6172. Min Act: -0.1700
Data Index: 2898872 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.6485. Min Act: -0.1700
Data Index: 8746620 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.6485. Min Act: -0.1700
Data Index: 1538682 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.5860. Min Act: -0.1700
Data Index: 1138086 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.6172. Min Act: -0.1700
Data Index: 1218469 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.5860. Min Act: -0.1700
Data Index: 2851943 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3672. Min Range: -8.3672
Max Act: 7.5547. Min Act: -0.1700
Data Index: 1681778 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19