Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4479 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5299. Min Range: -7.5299
Max Act: 7.5299. Min Act: -0.1700
Data Index: 3609221 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.9986. Min Act: -0.1700
Data Index: 8816076 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.9049. Min Act: -0.1700
Data Index: 4005813 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.9361. Min Act: -0.1700
Data Index: 7367142 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.7486. Min Act: -0.1700
Data Index: 8574397 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.6549. Min Act: -0.1700
Data Index: 2187848 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.4986. Min Act: -0.1700
Data Index: 7131270 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.5299. Min Act: -0.1700
Data Index: 8259184 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.4986. Min Act: -0.1700
Data Index: 2014086 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.4986. Min Act: -0.1700
Data Index: 3609236 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.4986. Min Act: -0.1700
Data Index: 2117682 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.5299. Min Act: -0.1700
Data Index: 230275 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.4674. Min Act: -0.1700
Data Index: 6127027 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.4674. Min Act: -0.1700
Data Index: 593811 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.4674. Min Act: -0.1700
Data Index: 6260206 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.4361. Min Act: -0.1700
Data Index: 4275383 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.4361. Min Act: -0.1700
Data Index: 8224155 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.4049. Min Act: -0.1700
Data Index: 3133032 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.3736. Min Act: -0.1700
Data Index: 6538863 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5299. Min Range: -7.5299
Max Act: 6.3736. Min Act: -0.1700
Data Index: 7096428 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19