Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3822 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.7259. Min Act: -0.1700
Data Index: 256787 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.7259. Min Act: -0.1700
Data Index: 7076861 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6946. Min Act: -0.1700
Data Index: 2667132 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6633. Min Act: -0.1700
Data Index: 544798 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6946. Min Act: -0.1700
Data Index: 8730428 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6946. Min Act: -0.1700
Data Index: 6567110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6633. Min Act: -0.1700
Data Index: 2315933 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6633. Min Act: -0.1700
Data Index: 5576926 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6633. Min Act: -0.1700
Data Index: 2410834 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6633. Min Act: -0.1700
Data Index: 3465708 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6633. Min Act: -0.1700
Data Index: 8706111 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6633. Min Act: -0.1700
Data Index: 6212571 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6007. Min Act: -0.1700
Data Index: 4783550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6320. Min Act: -0.1700
Data Index: 1132081 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6320. Min Act: -0.1700
Data Index: 4172249 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6320. Min Act: -0.1700
Data Index: 1370220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6320. Min Act: -0.1700
Data Index: 8265378 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6320. Min Act: -0.1700
Data Index: 5835519 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6320. Min Act: -0.1700
Data Index: 2623830 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6007. Min Act: -0.1700
Data Index: 6178395 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19