Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5544 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1642. Min Range: -7.1642
Max Act: 7.1642. Min Act: -0.1700
Data Index: 8109875 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.6955. Min Act: -0.1700
Data Index: 3493552 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.6017. Min Act: -0.1700
Data Index: 4019849 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.5705. Min Act: -0.1700
Data Index: 7631214 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.5705. Min Act: -0.1700
Data Index: 28027 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.5080. Min Act: -0.1700
Data Index: 4496615 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.5080. Min Act: -0.1700
Data Index: 1920267 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.5080. Min Act: -0.1700
Data Index: 1380774 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.4455. Min Act: -0.1700
Data Index: 1738201 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.4142. Min Act: -0.1700
Data Index: 7868652 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.3830. Min Act: -0.1700
Data Index: 287433 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.3517. Min Act: -0.1700
Data Index: 8311923 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.3517. Min Act: -0.1700
Data Index: 2385446 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.3517. Min Act: -0.1700
Data Index: 5955407 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.3205. Min Act: -0.1700
Data Index: 3189099 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.3205. Min Act: -0.1700
Data Index: 50162 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.2892. Min Act: -0.1700
Data Index: 6493281 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.3205. Min Act: -0.1700
Data Index: 6027645 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.2580. Min Act: -0.1700
Data Index: 2300828 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1642. Min Range: -7.1642
Max Act: 6.2580. Min Act: -0.1700
Data Index: 5650995 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19