Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3410 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.9536. Min Act: -0.1700
Data Index: 6234275 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.9536. Min Act: -0.1700
Data Index: 786280 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.9536. Min Act: -0.1700
Data Index: 4330018 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.9224. Min Act: -0.1700
Data Index: 6776914 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.9224. Min Act: -0.1700
Data Index: 2084988 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.9224. Min Act: -0.1700
Data Index: 5765265 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.9224. Min Act: -0.1700
Data Index: 5507027 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.8911. Min Act: -0.1700
Data Index: 7446551 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.8911. Min Act: -0.1700
Data Index: 3089390 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.8911. Min Act: -0.1700
Data Index: 4618300 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.9224. Min Act: -0.1700
Data Index: 2552254 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.8911. Min Act: -0.1700
Data Index: 197004 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.8911. Min Act: -0.1700
Data Index: 5467819 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.8911. Min Act: -0.1700
Data Index: 1318990 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.8911. Min Act: -0.1700
Data Index: 8497103 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.8598. Min Act: -0.1700
Data Index: 2353557 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.8598. Min Act: -0.1700
Data Index: 970442 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.8598. Min Act: -0.1700
Data Index: 5193450 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.8598. Min Act: -0.1700
Data Index: 5121951 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9536. Min Range: -3.9536
Max Act: 3.8598. Min Act: -0.1700
Data Index: 1712467 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19