Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.3139. Min Act: -0.1700
Data Index: 6032488 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.2514. Min Act: -0.1700
Data Index: 2649699 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.1264. Min Act: -0.1700
Data Index: 1853923 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0639. Min Act: -0.1700
Data Index: 3078213 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0639. Min Act: -0.1700
Data Index: 1433247 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0014. Min Act: -0.1700
Data Index: 2643926 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3139. Min Range: -7.3139
Max Act: 7.0014. Min Act: -0.1700
Data Index: 1457218 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3139. Min Range: -7.3139
Max Act: 6.9076. Min Act: -0.1700
Data Index: 7073287 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3139. Min Range: -7.3139
Max Act: 6.9076. Min Act: -0.1700
Data Index: 4429833 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3139. Min Range: -7.3139
Max Act: 6.9076. Min Act: -0.1700
Data Index: 6874907 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3139. Min Range: -7.3139
Max Act: 6.9076. Min Act: -0.1700
Data Index: 342922 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3139. Min Range: -7.3139
Max Act: 6.8764. Min Act: -0.1700
Data Index: 5869382 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3139. Min Range: -7.3139
Max Act: 6.8764. Min Act: -0.1700
Data Index: 2631592 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3139. Min Range: -7.3139
Max Act: 6.8451. Min Act: -0.1700
Data Index: 8735653 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3139. Min Range: -7.3139
Max Act: 6.8451. Min Act: -0.1700
Data Index: 2988548 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3139. Min Range: -7.3139
Max Act: 6.8139. Min Act: -0.1700
Data Index: 6795513 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3139. Min Range: -7.3139
Max Act: 6.8451. Min Act: -0.1700
Data Index: 1216432 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3139. Min Range: -7.3139
Max Act: 6.8139. Min Act: -0.1700
Data Index: 1911772 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3139. Min Range: -7.3139
Max Act: 6.7826. Min Act: -0.1700
Data Index: 7753478 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3139. Min Range: -7.3139
Max Act: 6.7826. Min Act: -0.1700
Data Index: 4110200 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19