Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5747 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9156. Min Range: -8.9156
Max Act: 8.9156. Min Act: -0.1700
Data Index: 1968056 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9156. Min Range: -8.9156
Max Act: 8.7281. Min Act: -0.1700
Data Index: 6140237 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9156. Min Range: -8.9156
Max Act: 8.5406. Min Act: -0.1700
Data Index: 4507349 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9156. Min Range: -8.9156
Max Act: 8.2906. Min Act: -0.1700
Data Index: 7955957 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9156. Min Range: -8.9156
Max Act: 8.1343. Min Act: -0.1700
Data Index: 6024356 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9156. Min Range: -8.9156
Max Act: 8.0718. Min Act: -0.1700
Data Index: 3355330 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9156. Min Range: -8.9156
Max Act: 8.0406. Min Act: -0.1700
Data Index: 2468092 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9156. Min Range: -8.9156
Max Act: 8.0406. Min Act: -0.1700
Data Index: 5571923 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9156. Min Range: -8.9156
Max Act: 8.0406. Min Act: -0.1700
Data Index: 4899307 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9156. Min Range: -8.9156
Max Act: 7.9781. Min Act: -0.1700
Data Index: 2877209 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9156. Min Range: -8.9156
Max Act: 7.9468. Min Act: -0.1700
Data Index: 7937808 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9156. Min Range: -8.9156
Max Act: 7.9468. Min Act: -0.1700
Data Index: 7445779 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9156. Min Range: -8.9156
Max Act: 7.8218. Min Act: -0.1700
Data Index: 121530 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9156. Min Range: -8.9156
Max Act: 7.8531. Min Act: -0.1700
Data Index: 333890 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9156. Min Range: -8.9156
Max Act: 7.8218. Min Act: -0.1700
Data Index: 1851283 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9156. Min Range: -8.9156
Max Act: 7.8218. Min Act: -0.1700
Data Index: 1336888 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9156. Min Range: -8.9156
Max Act: 7.7906. Min Act: -0.1700
Data Index: 7867809 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9156. Min Range: -8.9156
Max Act: 7.7281. Min Act: -0.1700
Data Index: 7724832 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9156. Min Range: -8.9156
Max Act: 7.6968. Min Act: -0.1700
Data Index: 825322 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9156. Min Range: -8.9156
Max Act: 7.6968. Min Act: -0.1700
Data Index: 3884773 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19