Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1504 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.6068. Min Act: -0.1700
Data Index: 7777203 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.5443. Min Act: -0.1700
Data Index: 3395651 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.4818. Min Act: -0.1700
Data Index: 5002411 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.4193. Min Act: -0.1700
Data Index: 3895425 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.2943. Min Act: -0.1700
Data Index: 5857412 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.3568. Min Act: -0.1700
Data Index: 1276035 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.3568. Min Act: -0.1700
Data Index: 7020996 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.3568. Min Act: -0.1700
Data Index: 3944889 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.2943. Min Act: -0.1700
Data Index: 4092348 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.2943. Min Act: -0.1700
Data Index: 4078152 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.2943. Min Act: -0.1700
Data Index: 4985680 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.2943. Min Act: -0.1700
Data Index: 618979 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.2943. Min Act: -0.1700
Data Index: 1805291 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.2318. Min Act: -0.1700
Data Index: 8569778 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.2318. Min Act: -0.1700
Data Index: 2396130 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.2318. Min Act: -0.1700
Data Index: 3481473 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.2318. Min Act: -0.1700
Data Index: 1332009 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.2318. Min Act: -0.1700
Data Index: 6926291 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.2318. Min Act: -0.1700
Data Index: 1554942 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6068. Min Range: -11.6068
Max Act: 11.1693. Min Act: -0.1700
Data Index: 4820577 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19