Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4005 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5795. Min Range: -7.5795
Max Act: 7.5795. Min Act: -0.1700
Data Index: 1974470 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5795. Min Range: -7.5795
Max Act: 7.5795. Min Act: -0.1700
Data Index: 7740976 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5795. Min Range: -7.5795
Max Act: 7.3607. Min Act: -0.1700
Data Index: 5536016 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5795. Min Range: -7.5795
Max Act: 7.2357. Min Act: -0.1700
Data Index: 4240520 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5795. Min Range: -7.5795
Max Act: 7.0482. Min Act: -0.1700
Data Index: 4181108 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5795. Min Range: -7.5795
Max Act: 7.0482. Min Act: -0.1700
Data Index: 6391978 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5795. Min Range: -7.5795
Max Act: 7.0170. Min Act: -0.1700
Data Index: 2977250 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5795. Min Range: -7.5795
Max Act: 6.9857. Min Act: -0.1700
Data Index: 5576669 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5795. Min Range: -7.5795
Max Act: 6.8920. Min Act: -0.1700
Data Index: 8620876 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5795. Min Range: -7.5795
Max Act: 6.8607. Min Act: -0.1700
Data Index: 168794 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5795. Min Range: -7.5795
Max Act: 6.8607. Min Act: -0.1700
Data Index: 1704335 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5795. Min Range: -7.5795
Max Act: 6.8295. Min Act: -0.1700
Data Index: 5698612 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5795. Min Range: -7.5795
Max Act: 6.8295. Min Act: -0.1700
Data Index: 3693821 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5795. Min Range: -7.5795
Max Act: 6.8295. Min Act: -0.1700
Data Index: 5570835 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5795. Min Range: -7.5795
Max Act: 6.7982. Min Act: -0.1700
Data Index: 6135825 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5795. Min Range: -7.5795
Max Act: 6.8295. Min Act: -0.1700
Data Index: 1990364 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5795. Min Range: -7.5795
Max Act: 6.7670. Min Act: -0.1700
Data Index: 7949597 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5795. Min Range: -7.5795
Max Act: 6.7670. Min Act: -0.1700
Data Index: 4054906 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5795. Min Range: -7.5795
Max Act: 6.7982. Min Act: -0.1700
Data Index: 8577693 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5795. Min Range: -7.5795
Max Act: 6.7670. Min Act: -0.1700
Data Index: 1243411 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19