Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2700 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.6000. Min Act: -0.1700
Data Index: 151822 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.4750. Min Act: -0.1700
Data Index: 4934101 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.3812. Min Act: -0.1700
Data Index: 2478338 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.3812. Min Act: -0.1700
Data Index: 8766483 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.3500. Min Act: -0.1700
Data Index: 2346093 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.3812. Min Act: -0.1700
Data Index: 4566379 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.3812. Min Act: -0.1700
Data Index: 2244866 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.2875. Min Act: -0.1700
Data Index: 8573788 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.2875. Min Act: -0.1700
Data Index: 6374469 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.2562. Min Act: -0.1700
Data Index: 6347670 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.2875. Min Act: -0.1700
Data Index: 6743787 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.2562. Min Act: -0.1700
Data Index: 6374468 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.2562. Min Act: -0.1700
Data Index: 2729466 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.2250. Min Act: -0.1700
Data Index: 5669507 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.2562. Min Act: -0.1700
Data Index: 726062 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.1937. Min Act: -0.1700
Data Index: 6820206 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.1937. Min Act: -0.1700
Data Index: 4805739 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.2250. Min Act: -0.1700
Data Index: 6537835 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.1937. Min Act: -0.1700
Data Index: 1125369 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.1312. Min Act: -0.1700
Data Index: 6379187 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19