Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3178 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8667. Min Range: -9.8667
Max Act: 9.8667. Min Act: -0.1700
Data Index: 6876186 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8667. Min Range: -9.8667
Max Act: 9.5542. Min Act: -0.1699
Data Index: 1483101 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8667. Min Range: -9.8667
Max Act: 9.2417. Min Act: -0.1700
Data Index: 603034 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8667. Min Range: -9.8667
Max Act: 9.1167. Min Act: -0.1700
Data Index: 4690283 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8667. Min Range: -9.8667
Max Act: 9.0542. Min Act: -0.1700
Data Index: 545160 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.9917. Min Act: -0.1700
Data Index: 1943621 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.9292. Min Act: -0.1700
Data Index: 4213073 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.9292. Min Act: -0.1700
Data Index: 8439974 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.9292. Min Act: -0.1700
Data Index: 2313304 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.8667. Min Act: -0.1700
Data Index: 4925993 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.8667. Min Act: -0.1700
Data Index: 4445805 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.8667. Min Act: -0.1700
Data Index: 3585619 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.8667. Min Act: -0.1699
Data Index: 2294881 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.8667. Min Act: -0.1700
Data Index: 3051548 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.8667. Min Act: -0.1700
Data Index: 7473482 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.8667. Min Act: -0.1700
Data Index: 1481458 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.8667. Min Act: -0.1700
Data Index: 2677739 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.8042. Min Act: -0.1700
Data Index: 4061889 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.8667. Min Act: -0.1700
Data Index: 490969 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8667. Min Range: -9.8667
Max Act: 8.8042. Min Act: -0.1700
Data Index: 7356845 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19