Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3349. Min Range: -6.3349
Max Act: 6.3349. Min Act: -0.1700
Data Index: 2050287 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.9599. Min Act: -0.1700
Data Index: 6536580 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.9287. Min Act: -0.1700
Data Index: 8420540 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.8974. Min Act: -0.1700
Data Index: 6042676 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.7412. Min Act: -0.1700
Data Index: 6256140 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.7724. Min Act: -0.1700
Data Index: 1685769 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.7412. Min Act: -0.1700
Data Index: 621908 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.7412. Min Act: -0.1700
Data Index: 239726 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.7412. Min Act: -0.1700
Data Index: 7085981 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.6787. Min Act: -0.1700
Data Index: 5525320 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.6787. Min Act: -0.1700
Data Index: 7105266 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.6787. Min Act: -0.1700
Data Index: 6765080 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.6787. Min Act: -0.1700
Data Index: 5298989 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.6162. Min Act: -0.1700
Data Index: 3362655 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.5849. Min Act: -0.1700
Data Index: 1716433 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.5537. Min Act: -0.1700
Data Index: 3608456 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.5849. Min Act: -0.1700
Data Index: 2092569 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.5537. Min Act: -0.1700
Data Index: 7932082 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.5537. Min Act: -0.1700
Data Index: 526789 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3349. Min Range: -6.3349
Max Act: 5.5537. Min Act: -0.1700
Data Index: 4849086 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19