Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3511 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6974. Min Range: -6.6974
Max Act: 6.6974. Min Act: -0.1700
Data Index: 2329913 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6974. Min Range: -6.6974
Max Act: 6.2911. Min Act: -0.1700
Data Index: 5521681 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6974. Min Range: -6.6974
Max Act: 6.1036. Min Act: -0.1700
Data Index: 7271282 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6974. Min Range: -6.6974
Max Act: 6.0724. Min Act: -0.1700
Data Index: 3171990 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6974. Min Range: -6.6974
Max Act: 6.0724. Min Act: -0.1700
Data Index: 7605947 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6974. Min Range: -6.6974
Max Act: 6.0099. Min Act: -0.1700
Data Index: 109616 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6974. Min Range: -6.6974
Max Act: 6.0411. Min Act: -0.1700
Data Index: 5929440 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6974. Min Range: -6.6974
Max Act: 6.0099. Min Act: -0.1700
Data Index: 278072 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6974. Min Range: -6.6974
Max Act: 6.0099. Min Act: -0.1700
Data Index: 5127195 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6974. Min Range: -6.6974
Max Act: 6.0099. Min Act: -0.1700
Data Index: 4430862 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6974. Min Range: -6.6974
Max Act: 5.9474. Min Act: -0.1700
Data Index: 8053256 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6974. Min Range: -6.6974
Max Act: 5.9474. Min Act: -0.1700
Data Index: 6262821 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6974. Min Range: -6.6974
Max Act: 5.9474. Min Act: -0.1700
Data Index: 3497254 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6974. Min Range: -6.6974
Max Act: 5.9474. Min Act: -0.1700
Data Index: 185234 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6974. Min Range: -6.6974
Max Act: 5.9161. Min Act: -0.1700
Data Index: 6146152 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6974. Min Range: -6.6974
Max Act: 5.9161. Min Act: -0.1700
Data Index: 7784435 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6974. Min Range: -6.6974
Max Act: 5.8849. Min Act: -0.1700
Data Index: 6162916 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6974. Min Range: -6.6974
Max Act: 5.9161. Min Act: -0.1700
Data Index: 6325773 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6974. Min Range: -6.6974
Max Act: 5.8849. Min Act: -0.1700
Data Index: 7113933 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6974. Min Range: -6.6974
Max Act: 5.9161. Min Act: -0.1700
Data Index: 138123 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19