Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4750 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.3490. Min Act: -0.1700
Data Index: 7736491 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.3803. Min Act: -0.1700
Data Index: 8477973 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.3803. Min Act: -0.1700
Data Index: 6090960 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.3490. Min Act: -0.1700
Data Index: 5326536 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.3490. Min Act: -0.1700
Data Index: 3570254 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.2865. Min Act: -0.1700
Data Index: 5878510 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.2865. Min Act: -0.1700
Data Index: 3555078 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.2240. Min Act: -0.1700
Data Index: 6016050 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.1928. Min Act: -0.1700
Data Index: 3388203 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.1928. Min Act: -0.1700
Data Index: 5063559 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.1615. Min Act: -0.1700
Data Index: 3989916 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.1928. Min Act: -0.1700
Data Index: 5944921 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.1928. Min Act: -0.1700
Data Index: 6239002 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.1615. Min Act: -0.1700
Data Index: 2592262 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.1615. Min Act: -0.1700
Data Index: 176504 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.1615. Min Act: -0.1700
Data Index: 1691980 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.1615. Min Act: -0.1700
Data Index: 225751 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.1615. Min Act: -0.1700
Data Index: 7373453 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.1615. Min Act: -0.1700
Data Index: 5478068 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3803. Min Range: -6.3803
Max Act: 6.1303. Min Act: -0.1700
Data Index: 6321240 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19