Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1544 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1743. Min Range: -7.1743
Max Act: 7.1743. Min Act: -0.1700
Data Index: 8148865 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.7993. Min Act: -0.1700
Data Index: 6867569 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.7680. Min Act: -0.1700
Data Index: 4733736 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.7055. Min Act: -0.1700
Data Index: 1971566 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.7368. Min Act: -0.1700
Data Index: 3516574 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.6430. Min Act: -0.1700
Data Index: 5540532 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.5805. Min Act: -0.1700
Data Index: 2792082 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.5180. Min Act: -0.1700
Data Index: 7007504 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.5493. Min Act: -0.1700
Data Index: 8748889 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.5180. Min Act: -0.1700
Data Index: 7524013 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.5180. Min Act: -0.1700
Data Index: 4968286 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.5180. Min Act: -0.1700
Data Index: 3162220 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.5493. Min Act: -0.1700
Data Index: 7089302 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.5180. Min Act: -0.1700
Data Index: 3648239 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.4868. Min Act: -0.1700
Data Index: 1894079 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.4868. Min Act: -0.1700
Data Index: 3319913 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.4868. Min Act: -0.1700
Data Index: 5626481 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.4868. Min Act: -0.1700
Data Index: 7203226 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.4868. Min Act: -0.1700
Data Index: 7273200 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1743. Min Range: -7.1743
Max Act: 6.4868. Min Act: -0.1700
Data Index: 4841328 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19