Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4625 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2890. Min Act: -0.1700
Data Index: 82447 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2890. Min Act: -0.1700
Data Index: 1767180 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2890. Min Act: -0.1700
Data Index: 2556078 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2890. Min Act: -0.1700
Data Index: 622190 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2890. Min Act: -0.1700
Data Index: 5537915 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2576. Min Act: -0.1700
Data Index: 4862996 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2576. Min Act: -0.1700
Data Index: 8706954 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2576. Min Act: -0.1700
Data Index: 319641 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2262. Min Act: -0.1700
Data Index: 4661285 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2576. Min Act: -0.1700
Data Index: 4622400 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2576. Min Act: -0.1700
Data Index: 4343596 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2576. Min Act: -0.1700
Data Index: 3598145 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2576. Min Act: -0.1700
Data Index: 3329084 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2576. Min Act: -0.1700
Data Index: 2799366 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2576. Min Act: -0.1700
Data Index: 1865386 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2262. Min Act: -0.1700
Data Index: 1251563 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2262. Min Act: -0.1700
Data Index: 1005408 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2262. Min Act: -0.1700
Data Index: 1032685 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2262. Min Act: -0.1700
Data Index: 216819 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2890. Min Range: -3.2890
Max Act: 3.2262. Min Act: -0.1699
Data Index: 98417 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19