Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1640 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.8434. Min Act: -0.1700
Data Index: 7684582 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.8434. Min Act: -0.1700
Data Index: 3281152 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.8097. Min Act: -0.1700
Data Index: 3855300 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.8013. Min Act: -0.1700
Data Index: 6145304 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.8097. Min Act: -0.1700
Data Index: 5207878 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.8013. Min Act: -0.1700
Data Index: 8609730 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.8013. Min Act: -0.1700
Data Index: 4101386 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.8013. Min Act: -0.1700
Data Index: 150350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.7929. Min Act: -0.1700
Data Index: 4446205 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.7845. Min Act: -0.1700
Data Index: 3391289 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.7845. Min Act: -0.1700
Data Index: 5936284 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.7845. Min Act: -0.1700
Data Index: 4434581 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.7845. Min Act: -0.1700
Data Index: 3113794 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.7845. Min Act: -0.1700
Data Index: 264289 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.7845. Min Act: -0.1700
Data Index: 3753132 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.7845. Min Act: -0.1700
Data Index: 3295410 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.7845. Min Act: -0.1694
Data Index: 4297085 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.7845. Min Act: -0.1700
Data Index: 8167124 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.7762. Min Act: -0.1700
Data Index: 7207522 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8434. Min Range: -0.8434
Max Act: 0.7762. Min Act: -0.1700
Data Index: 2036766 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19