Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1642 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5361. Min Act: -0.1700
Data Index: 3643291 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5361. Min Act: -0.1700
Data Index: 1491555 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 1568071 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 7464164 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5361. Min Act: -0.1700
Data Index: 5458812 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 5164365 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 4318518 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 4162783 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5361. Min Act: -0.1700
Data Index: 3930809 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 3803652 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 3159401 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 2087199 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 769040 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 1457814 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 1029113 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 2635361 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 625697 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5361. Min Act: -0.1700
Data Index: 2536068 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 2514027 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5361. Min Range: -4.5361
Max Act: 4.5049. Min Act: -0.1700
Data Index: 2167689 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19