Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 681 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0764. Min Range: -6.0764
Max Act: 6.0764. Min Act: -0.1700
Data Index: 4329115 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.8889. Min Act: -0.1700
Data Index: 5789716 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.8264. Min Act: -0.1700
Data Index: 1098727 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.7951. Min Act: -0.1700
Data Index: 664676 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.7951. Min Act: -0.1696
Data Index: 7531344 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.7951. Min Act: -0.1700
Data Index: 5995450 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.7951. Min Act: -0.1697
Data Index: 8644346 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.7014. Min Act: -0.1700
Data Index: 7620458 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.7014. Min Act: -0.1700
Data Index: 8524541 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.7014. Min Act: -0.1700
Data Index: 7087257 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.6701. Min Act: -0.1700
Data Index: 6711056 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.7014. Min Act: -0.1700
Data Index: 2087969 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.6701. Min Act: -0.1700
Data Index: 8220786 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.6701. Min Act: -0.1700
Data Index: 3740508 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.6701. Min Act: -0.1700
Data Index: 3747250 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.6701. Min Act: -0.1700
Data Index: 7570528 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.6701. Min Act: -0.1699
Data Index: 6784117 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.6701. Min Act: -0.1700
Data Index: 2639722 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.6389. Min Act: -0.1699
Data Index: 4617011 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0764. Min Range: -6.0764
Max Act: 5.6389. Min Act: -0.1700
Data Index: 5403412 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19