Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2220 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.5423. Min Act: -0.1700
Data Index: 7710015 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.3548. Min Act: -0.1700
Data Index: 7749094 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.3548. Min Act: -0.1700
Data Index: 6674417 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.3236. Min Act: -0.1700
Data Index: 3906603 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.3236. Min Act: -0.1700
Data Index: 5497302 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.2923. Min Act: -0.1700
Data Index: 6421958 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.2923. Min Act: -0.1700
Data Index: 4187987 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.2298. Min Act: -0.1700
Data Index: 2252540 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.1986. Min Act: -0.1700
Data Index: 266416 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.1673. Min Act: -0.1700
Data Index: 7412005 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.1361. Min Act: -0.1700
Data Index: 5516559 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.1048. Min Act: -0.1700
Data Index: 6606552 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.1048. Min Act: -0.1700
Data Index: 7584788 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.0736. Min Act: -0.1700
Data Index: 3505790 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.0423. Min Act: -0.1700
Data Index: 6290196 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.0423. Min Act: -0.1700
Data Index: 4127345 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.0111. Min Act: -0.1700
Data Index: 1594559 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.0111. Min Act: -0.1700
Data Index: 1696870 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.0111. Min Act: -0.1700
Data Index: 1067565 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5423. Min Range: -6.5423
Max Act: 6.0111. Min Act: -0.1700
Data Index: 6601189 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19