Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3331 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.9206. Min Act: -0.1700
Data Index: 927571 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.8581. Min Act: -0.1700
Data Index: 4171673 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.7643. Min Act: -0.1700
Data Index: 3711049 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.7643. Min Act: -0.1700
Data Index: 714674 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.7331. Min Act: -0.1700
Data Index: 5974159 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.7331. Min Act: -0.1700
Data Index: 5951376 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.7018. Min Act: -0.1700
Data Index: 6226104 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.7018. Min Act: -0.1700
Data Index: 7455924 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.7018. Min Act: -0.1700
Data Index: 1024178 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.6706. Min Act: -0.1700
Data Index: 4761232 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.6706. Min Act: -0.1700
Data Index: 6319493 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.6706. Min Act: -0.1700
Data Index: 1217016 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.6393. Min Act: -0.1700
Data Index: 5623034 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.6393. Min Act: -0.1700
Data Index: 1360031 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.6393. Min Act: -0.1700
Data Index: 221783 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.6081. Min Act: -0.1700
Data Index: 3629509 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.6081. Min Act: -0.1700
Data Index: 6114107 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.6081. Min Act: -0.1700
Data Index: 365957 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.5768. Min Act: -0.1700
Data Index: 8328810 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9206. Min Range: -5.9206
Max Act: 5.5768. Min Act: -0.1700
Data Index: 4713590 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19