Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2009 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.9584. Min Act: -0.1700
Data Index: 4332585 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.9268. Min Act: -0.1700
Data Index: 4773090 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.9268. Min Act: -0.1700
Data Index: 5879281 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.8792. Min Act: -0.1700
Data Index: 8426802 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.8792. Min Act: -0.1700
Data Index: 3483821 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.8633. Min Act: -0.1700
Data Index: 3841545 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.8633. Min Act: -0.1700
Data Index: 7800277 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.8633. Min Act: -0.1700
Data Index: 5273139 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.8474. Min Act: -0.1700
Data Index: 1046622 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.8474. Min Act: -0.1700
Data Index: 8515914 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.8633. Min Act: -0.1700
Data Index: 2651156 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.8633. Min Act: -0.1700
Data Index: 5985632 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.8474. Min Act: -0.1700
Data Index: 4285935 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.8316. Min Act: -0.1700
Data Index: 534229 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.8316. Min Act: -0.1699
Data Index: 437468 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.8156. Min Act: -0.1700
Data Index: 8533800 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.8156. Min Act: -0.1700
Data Index: 4076181 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.7997. Min Act: -0.1700
Data Index: 529820 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.7997. Min Act: -0.1700
Data Index: 1856520 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9584. Min Range: -2.9584
Max Act: 2.7838. Min Act: -0.1700
Data Index: 520039 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19