Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2369 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.3841. Min Act: -0.1700
Data Index: 3123578 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.3527. Min Act: -0.1700
Data Index: 7436872 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.3527. Min Act: -0.1700
Data Index: 8005331 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.3370. Min Act: -0.1700
Data Index: 6422508 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.3370. Min Act: -0.1700
Data Index: 4435904 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.3056. Min Act: -0.1700
Data Index: 6266915 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.2899. Min Act: -0.1700
Data Index: 5191474 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.3370. Min Act: -0.1700
Data Index: 2135164 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.2899. Min Act: -0.1700
Data Index: 5779716 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.2899. Min Act: -0.1700
Data Index: 6843117 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.2742. Min Act: -0.1700
Data Index: 3044615 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.2742. Min Act: -0.1700
Data Index: 2532004 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.2742. Min Act: -0.1700
Data Index: 6218944 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.2742. Min Act: -0.1700
Data Index: 3638006 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.2899. Min Act: -0.1700
Data Index: 688988 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.2899. Min Act: -0.1700
Data Index: 7083737 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.2742. Min Act: -0.1700
Data Index: 4657061 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.2899. Min Act: -0.1700
Data Index: 1921594 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.2742. Min Act: -0.1700
Data Index: 8321621 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3841. Min Range: -3.3841
Max Act: 3.2742. Min Act: -0.1700
Data Index: 3296294 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19