Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2430 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.6037. Min Act: -0.1700
Data Index: 5053002 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.5412. Min Act: -0.1700
Data Index: 8190867 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.5412. Min Act: -0.1700
Data Index: 5418071 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.5412. Min Act: -0.1700
Data Index: 5006977 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.5099. Min Act: -0.1700
Data Index: 1215566 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.4474. Min Act: -0.1700
Data Index: 4997930 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.3849. Min Act: -0.1700
Data Index: 2538042 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.4162. Min Act: -0.1700
Data Index: 5689689 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.4162. Min Act: -0.1700
Data Index: 7175573 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.4162. Min Act: -0.1700
Data Index: 7903487 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.4162. Min Act: -0.1700
Data Index: 3272876 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.4162. Min Act: -0.1700
Data Index: 627575 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.3537. Min Act: -0.1700
Data Index: 2355901 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.3537. Min Act: -0.1700
Data Index: 5504283 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.3537. Min Act: -0.1700
Data Index: 123555 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.3849. Min Act: -0.1700
Data Index: 7993329 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.3537. Min Act: -0.1700
Data Index: 2951725 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.3537. Min Act: -0.1700
Data Index: 8349009 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.3224. Min Act: -0.1700
Data Index: 7057285 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6037. Min Range: -6.6037
Max Act: 6.2912. Min Act: -0.1700
Data Index: 4618044 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19