Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3743 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.6444. Min Act: -0.1686
Data Index: 2895130 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.6444. Min Act: -0.1697
Data Index: 7935733 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.6444. Min Act: -0.1700
Data Index: 7679637 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.6444. Min Act: -0.1700
Data Index: 2736881 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.6444. Min Act: -0.1699
Data Index: 5736111 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.6444. Min Act: -0.1698
Data Index: 319416 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.6444. Min Act: -0.1692
Data Index: 7388146 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.4870. Min Act: -0.1700
Data Index: 2959600 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.4870. Min Act: -0.1700
Data Index: 1340507 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.4870. Min Act: -0.1693
Data Index: 2797050 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.4870. Min Act: -0.1664
Data Index: 7460188 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.4870. Min Act: -0.1684
Data Index: 6912956 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.4870. Min Act: -0.1649
Data Index: 6771393 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.4870. Min Act: -0.1674
Data Index: 6722368 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.4870. Min Act: -0.1700
Data Index: 4429943 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.4870. Min Act: -0.1700
Data Index: 3752750 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.4870. Min Act: -0.1700
Data Index: 3699725 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.4870. Min Act: -0.1600
Data Index: 1545780 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.4694. Min Act: -0.1668
Data Index: 1446438 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6444. Min Range: -1.6444
Max Act: 1.4694. Min Act: -0.1694
Data Index: 943845 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19