Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3765 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.9519. Min Act: -0.1700
Data Index: 2083641 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.9206. Min Act: -0.1700
Data Index: 8831447 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8894. Min Act: -0.1700
Data Index: 22068 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8894. Min Act: -0.1700
Data Index: 1866280 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8581. Min Act: -0.1700
Data Index: 8668285 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8581. Min Act: -0.1700
Data Index: 2677301 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8581. Min Act: -0.1700
Data Index: 5662426 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8268. Min Act: -0.1700
Data Index: 1273675 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8581. Min Act: -0.1700
Data Index: 4220374 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8581. Min Act: -0.1700
Data Index: 3874095 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8581. Min Act: -0.1700
Data Index: 8702563 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8581. Min Act: -0.1700
Data Index: 982182 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8581. Min Act: -0.1700
Data Index: 8436038 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8268. Min Act: -0.1700
Data Index: 683658 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8268. Min Act: -0.1700
Data Index: 136912 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8268. Min Act: -0.1700
Data Index: 1913282 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8268. Min Act: -0.1700
Data Index: 6219301 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8268. Min Act: -0.1700
Data Index: 243018 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8268. Min Act: -0.1700
Data Index: 447660 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9519. Min Range: -3.9519
Max Act: 3.8268. Min Act: -0.1700
Data Index: 6352445 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19