Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0331. Min Range: -5.0331
Max Act: 5.0331. Min Act: -0.1700
Data Index: 1572031 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0331. Min Range: -5.0331
Max Act: 5.0018. Min Act: -0.1700
Data Index: 6927211 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0331. Min Range: -5.0331
Max Act: 5.0018. Min Act: -0.1700
Data Index: 8437374 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9706. Min Act: -0.1700
Data Index: 6157825 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9706. Min Act: -0.1700
Data Index: 7625249 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0331. Min Range: -5.0331
Max Act: 5.0018. Min Act: -0.1700
Data Index: 5344102 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9706. Min Act: -0.1700
Data Index: 3620283 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9706. Min Act: -0.1700
Data Index: 5221828 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9393. Min Act: -0.1700
Data Index: 5823524 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9081. Min Act: -0.1700
Data Index: 4509311 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9706. Min Act: -0.1700
Data Index: 5958065 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9393. Min Act: -0.1700
Data Index: 7546681 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9393. Min Act: -0.1700
Data Index: 1213543 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9393. Min Act: -0.1700
Data Index: 3216834 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9081. Min Act: -0.1700
Data Index: 1764867 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9081. Min Act: -0.1700
Data Index: 4648206 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9081. Min Act: -0.1700
Data Index: 5009642 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9081. Min Act: -0.1700
Data Index: 2216148 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9081. Min Act: -0.1700
Data Index: 1669498 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0331. Min Range: -5.0331
Max Act: 4.9081. Min Act: -0.1700
Data Index: 4446456 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19