Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1589 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7472. Min Range: -6.7472
Max Act: 6.7472. Min Act: -0.1700
Data Index: 8278522 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7472. Min Range: -6.7472
Max Act: 6.4659. Min Act: -0.1700
Data Index: 2253490 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7472. Min Range: -6.7472
Max Act: 6.3097. Min Act: -0.1700
Data Index: 6833348 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7472. Min Range: -6.7472
Max Act: 6.2159. Min Act: -0.1700
Data Index: 4001310 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7472. Min Range: -6.7472
Max Act: 6.1534. Min Act: -0.1700
Data Index: 6432369 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7472. Min Range: -6.7472
Max Act: 6.0597. Min Act: -0.1700
Data Index: 5228501 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7472. Min Range: -6.7472
Max Act: 5.9972. Min Act: -0.1700
Data Index: 2493500 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7472. Min Range: -6.7472
Max Act: 5.9972. Min Act: -0.1700
Data Index: 4252727 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7472. Min Range: -6.7472
Max Act: 6.0284. Min Act: -0.1700
Data Index: 4271544 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7472. Min Range: -6.7472
Max Act: 5.9659. Min Act: -0.1700
Data Index: 220601 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7472. Min Range: -6.7472
Max Act: 5.9659. Min Act: -0.1700
Data Index: 2060137 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7472. Min Range: -6.7472
Max Act: 5.9659. Min Act: -0.1700
Data Index: 1480353 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7472. Min Range: -6.7472
Max Act: 5.9659. Min Act: -0.1700
Data Index: 2566099 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7472. Min Range: -6.7472
Max Act: 5.9659. Min Act: -0.1700
Data Index: 2242098 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7472. Min Range: -6.7472
Max Act: 5.9347. Min Act: -0.1700
Data Index: 4937007 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7472. Min Range: -6.7472
Max Act: 5.9034. Min Act: -0.1700
Data Index: 3587984 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7472. Min Range: -6.7472
Max Act: 5.9347. Min Act: -0.1700
Data Index: 7490393 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7472. Min Range: -6.7472
Max Act: 5.9347. Min Act: -0.1700
Data Index: 6774926 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7472. Min Range: -6.7472
Max Act: 5.9347. Min Act: -0.1700
Data Index: 6329587 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7472. Min Range: -6.7472
Max Act: 5.9034. Min Act: -0.1700
Data Index: 6407651 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19