Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2542 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.6757. Min Act: -0.1700
Data Index: 8255388 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.6409. Min Act: -0.1700
Data Index: 4171388 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.6409. Min Act: -0.1700
Data Index: 3904513 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.5536. Min Act: -0.1698
Data Index: 6902437 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.5711. Min Act: -0.1700
Data Index: 1802755 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.5361. Min Act: -0.1700
Data Index: 5236416 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.5361. Min Act: -0.1700
Data Index: 1331893 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.5361. Min Act: -0.1700
Data Index: 6469921 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.5361. Min Act: -0.1691
Data Index: 6453099 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.5361. Min Act: -0.1468
Data Index: 5451072 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.5361. Min Act: -0.1598
Data Index: 1611655 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.5361. Min Act: -0.1677
Data Index: 797120 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.5361. Min Act: -0.1684
Data Index: 4051247 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.5361. Min Act: -0.1663
Data Index: 2134494 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.5361. Min Act: -0.1657
Data Index: 2010586 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.5361. Min Act: -0.1691
Data Index: 4434243 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.5361. Min Act: -0.1668
Data Index: 6508111 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.4834. Min Act: -0.1700
Data Index: 6460855 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.4483. Min Act: -0.1700
Data Index: 4792571 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6757. Min Range: -1.6757
Max Act: 1.4130. Min Act: -0.1700
Data Index: 7198589 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19