Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2165 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.2583. Min Act: -0.1700
Data Index: 6718913 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.1797. Min Act: -0.1700
Data Index: 1692311 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.1640. Min Act: -0.1700
Data Index: 3209198 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.1325. Min Act: -0.1700
Data Index: 4362446 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.1168. Min Act: -0.1700
Data Index: 52633 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.0537. Min Act: -0.1700
Data Index: 2359629 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.0537. Min Act: -0.1700
Data Index: 2754708 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.0537. Min Act: -0.1700
Data Index: 7545432 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.0379. Min Act: -0.1700
Data Index: 7005130 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.0537. Min Act: -0.1700
Data Index: 7129017 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.0221. Min Act: -0.1700
Data Index: 1998862 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.0221. Min Act: -0.1700
Data Index: 2736218 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.0221. Min Act: -0.1700
Data Index: 4961295 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.0221. Min Act: -0.1700
Data Index: 2561170 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2583. Min Range: -3.2583
Max Act: 3.0379. Min Act: -0.1700
Data Index: 5060345 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2583. Min Range: -3.2583
Max Act: 2.9905. Min Act: -0.1700
Data Index: 6181079 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2583. Min Range: -3.2583
Max Act: 2.9905. Min Act: -0.1700
Data Index: 3343347 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2583. Min Range: -3.2583
Max Act: 2.9747. Min Act: -0.1700
Data Index: 787930 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2583. Min Range: -3.2583
Max Act: 2.9747. Min Act: -0.1700
Data Index: 8611416 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2583. Min Range: -3.2583
Max Act: 2.9747. Min Act: -0.1700
Data Index: 4499 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19