Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 774 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.4863. Min Act: -0.1700
Data Index: 1762489 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.3300. Min Act: -0.1700
Data Index: 7239552 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.3300. Min Act: -0.1700
Data Index: 5083451 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.2988. Min Act: -0.1700
Data Index: 6299079 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.2675. Min Act: -0.1700
Data Index: 4646454 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.2675. Min Act: -0.1700
Data Index: 2983137 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.2363. Min Act: -0.1700
Data Index: 3370817 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.2363. Min Act: -0.1700
Data Index: 1449128 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.2363. Min Act: -0.1700
Data Index: 7211841 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.2363. Min Act: -0.1700
Data Index: 7058466 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.2050. Min Act: -0.1700
Data Index: 2983135 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.2363. Min Act: -0.1700
Data Index: 3777245 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.2363. Min Act: -0.1700
Data Index: 8373404 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.2050. Min Act: -0.1700
Data Index: 2147733 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.1738. Min Act: -0.1700
Data Index: 1244152 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.1738. Min Act: -0.1700
Data Index: 5478162 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.2050. Min Act: -0.1700
Data Index: 3115372 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.1738. Min Act: -0.1700
Data Index: 606155 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.1738. Min Act: -0.1700
Data Index: 235531 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4863. Min Range: -4.4863
Max Act: 4.1738. Min Act: -0.1700
Data Index: 7653159 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19