Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2069 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.7841. Min Act: -0.1700
Data Index: 5530020 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.7216. Min Act: -0.1700
Data Index: 6491971 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.5966. Min Act: -0.1700
Data Index: 5867542 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.5966. Min Act: -0.1700
Data Index: 4644210 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.5966. Min Act: -0.1700
Data Index: 6049684 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.5341. Min Act: -0.1700
Data Index: 7631855 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.2841. Min Act: -0.1700
Data Index: 4908028 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.2841. Min Act: -0.1700
Data Index: 3699792 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.3466. Min Act: -0.1700
Data Index: 7696184 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.2216. Min Act: -0.1700
Data Index: 5863624 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.2216. Min Act: -0.1700
Data Index: 1131583 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.2216. Min Act: -0.1700
Data Index: 3264212 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.1591. Min Act: -0.1700
Data Index: 6207760 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.2216. Min Act: -0.1700
Data Index: 5114806 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.2841. Min Act: -0.1700
Data Index: 6840810 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.2216. Min Act: -0.1700
Data Index: 1955748 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.2216. Min Act: -0.1700
Data Index: 5033705 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.0966. Min Act: -0.1700
Data Index: 3732770 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.0341. Min Act: -0.1700
Data Index: 7210827 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7841. Min Range: -8.7841
Max Act: 8.0966. Min Act: -0.1700
Data Index: 6837543 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19