Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3970 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0779. Min Range: -5.0779
Max Act: 5.0779. Min Act: -0.1700
Data Index: 4342585 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0779. Min Range: -5.0779
Max Act: 5.0154. Min Act: -0.1700
Data Index: 7825673 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.9529. Min Act: -0.1700
Data Index: 8227372 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.8904. Min Act: -0.1700
Data Index: 4289808 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.9217. Min Act: -0.1700
Data Index: 1291509 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.8592. Min Act: -0.1700
Data Index: 8600949 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.8592. Min Act: -0.1700
Data Index: 7641169 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.8279. Min Act: -0.1700
Data Index: 5259181 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.7967. Min Act: -0.1700
Data Index: 1752259 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.7967. Min Act: -0.1700
Data Index: 6399139 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.7654. Min Act: -0.1700
Data Index: 7163648 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.7654. Min Act: -0.1700
Data Index: 3925405 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.7654. Min Act: -0.1700
Data Index: 1263847 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.7342. Min Act: -0.1700
Data Index: 1299905 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.7342. Min Act: -0.1700
Data Index: 4707731 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.7342. Min Act: -0.1700
Data Index: 4813625 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.7029. Min Act: -0.1700
Data Index: 2075958 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.7342. Min Act: -0.1700
Data Index: 6785591 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.7342. Min Act: -0.1700
Data Index: 1756246 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0779. Min Range: -5.0779
Max Act: 4.7342. Min Act: -0.1700
Data Index: 2368962 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19