Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.8111. Min Act: -0.1700
Data Index: 8049707 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.8111. Min Act: -0.1700
Data Index: 430713 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.7799. Min Act: -0.1700
Data Index: 2641381 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.6236. Min Act: -0.1700
Data Index: 1673892 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.6549. Min Act: -0.1700
Data Index: 45544 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5924. Min Act: -0.1700
Data Index: 2928404 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5924. Min Act: -0.1700
Data Index: 6882079 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.4986. Min Act: -0.1700
Data Index: 3886497 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5299. Min Act: -0.1700
Data Index: 888065 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5299. Min Act: -0.1700
Data Index: 3300449 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5299. Min Act: -0.1700
Data Index: 342259 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.4674. Min Act: -0.1700
Data Index: 8552163 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.4674. Min Act: -0.1700
Data Index: 1883914 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.4361. Min Act: -0.1700
Data Index: 5187186 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.4049. Min Act: -0.1700
Data Index: 5001058 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.4049. Min Act: -0.1700
Data Index: 776247 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.4049. Min Act: -0.1700
Data Index: 2937334 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.3424. Min Act: -0.1700
Data Index: 5277586 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.3736. Min Act: -0.1700
Data Index: 7397157 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.3736. Min Act: -0.1700
Data Index: 6128456 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19