Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4480 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.8224. Min Act: -0.1700
Data Index: 5637579 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.6349. Min Act: -0.1700
Data Index: 7978636 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.6349. Min Act: -0.1700
Data Index: 1311916 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.6036. Min Act: -0.1700
Data Index: 6231800 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.5724. Min Act: -0.1700
Data Index: 2682458 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.4786. Min Act: -0.1700
Data Index: 6142558 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.4474. Min Act: -0.1700
Data Index: 6054807 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.5099. Min Act: -0.1700
Data Index: 4569813 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.4786. Min Act: -0.1700
Data Index: 660977 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.4474. Min Act: -0.1700
Data Index: 8571930 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.4474. Min Act: -0.1700
Data Index: 8734884 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.3849. Min Act: -0.1700
Data Index: 4492725 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.4161. Min Act: -0.1700
Data Index: 7447206 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.4161. Min Act: -0.1700
Data Index: 4694995 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.3849. Min Act: -0.1700
Data Index: 1387203 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.3849. Min Act: -0.1700
Data Index: 8264013 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.3224. Min Act: -0.1700
Data Index: 5547116 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.3536. Min Act: -0.1700
Data Index: 8136616 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.3224. Min Act: -0.1700
Data Index: 4866732 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8224. Min Range: -6.8224
Max Act: 6.2286. Min Act: -0.1700
Data Index: 5573903 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19