Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5110 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.6365. Min Act: -0.1700
Data Index: 2593988 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.6053. Min Act: -0.1700
Data Index: 5276831 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5740. Min Act: -0.1700
Data Index: 1622658 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5740. Min Act: -0.1700
Data Index: 7035665 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5740. Min Act: -0.1700
Data Index: 5869246 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5740. Min Act: -0.1700
Data Index: 2947650 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5428. Min Act: -0.1700
Data Index: 1136077 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5740. Min Act: -0.1700
Data Index: 4724628 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5740. Min Act: -0.1700
Data Index: 382242 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5740. Min Act: -0.1700
Data Index: 2309321 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5428. Min Act: -0.1700
Data Index: 151076 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5428. Min Act: -0.1700
Data Index: 274571 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5428. Min Act: -0.1700
Data Index: 5019346 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5428. Min Act: -0.1700
Data Index: 459500 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5428. Min Act: -0.1700
Data Index: 3835832 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5428. Min Act: -0.1699
Data Index: 1715950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5115. Min Act: -0.1700
Data Index: 6225115 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5428. Min Act: -0.1700
Data Index: 8173390 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5115. Min Act: -0.1700
Data Index: 3791970 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6365. Min Range: -5.6365
Max Act: 5.5115. Min Act: -0.1700
Data Index: 212748 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19