Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2755 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2825. Min Range: -9.2825
Max Act: 9.2825. Min Act: -0.1700
Data Index: 1305885 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2825. Min Range: -9.2825
Max Act: 9.2200. Min Act: -0.1700
Data Index: 4501303 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2825. Min Range: -9.2825
Max Act: 9.2200. Min Act: -0.1700
Data Index: 7571131 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2825. Min Range: -9.2825
Max Act: 9.1575. Min Act: -0.1700
Data Index: 1346625 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2825. Min Range: -9.2825
Max Act: 9.0950. Min Act: -0.1700
Data Index: 959876 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2825. Min Range: -9.2825
Max Act: 9.0325. Min Act: -0.1700
Data Index: 1654370 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2825. Min Range: -9.2825
Max Act: 8.9700. Min Act: -0.1700
Data Index: 1247287 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2825. Min Range: -9.2825
Max Act: 8.9700. Min Act: -0.1700
Data Index: 1357181 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2825. Min Range: -9.2825
Max Act: 8.9700. Min Act: -0.1700
Data Index: 5094853 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2825. Min Range: -9.2825
Max Act: 8.9075. Min Act: -0.1700
Data Index: 598425 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2825. Min Range: -9.2825
Max Act: 8.9075. Min Act: -0.1700
Data Index: 5783706 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2825. Min Range: -9.2825
Max Act: 8.8450. Min Act: -0.1700
Data Index: 3250982 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2825. Min Range: -9.2825
Max Act: 8.8450. Min Act: -0.1700
Data Index: 907689 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2825. Min Range: -9.2825
Max Act: 8.8450. Min Act: -0.1700
Data Index: 7560917 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2825. Min Range: -9.2825
Max Act: 8.8450. Min Act: -0.1700
Data Index: 1571400 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2825. Min Range: -9.2825
Max Act: 8.8450. Min Act: -0.1700
Data Index: 7772523 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2825. Min Range: -9.2825
Max Act: 8.7825. Min Act: -0.1700
Data Index: 832057 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2825. Min Range: -9.2825
Max Act: 8.7825. Min Act: -0.1700
Data Index: 3699027 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2825. Min Range: -9.2825
Max Act: 8.8450. Min Act: -0.1700
Data Index: 7766252 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2825. Min Range: -9.2825
Max Act: 8.7200. Min Act: -0.1700
Data Index: 1759978 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19