Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3747 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.9009. Min Act: -0.1700
Data Index: 5525075 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.8697. Min Act: -0.1700
Data Index: 2677013 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.8384. Min Act: -0.1700
Data Index: 496094 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.8072. Min Act: -0.1700
Data Index: 6703045 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.8072. Min Act: -0.1700
Data Index: 5183869 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.7447. Min Act: -0.1700
Data Index: 7572955 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.7134. Min Act: -0.1700
Data Index: 3844099 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.6509. Min Act: -0.1700
Data Index: 5566525 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.6509. Min Act: -0.1700
Data Index: 5340625 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.6509. Min Act: -0.1700
Data Index: 2057433 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.6509. Min Act: -0.1700
Data Index: 7764415 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.5884. Min Act: -0.1700
Data Index: 8570488 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.5572. Min Act: -0.1700
Data Index: 2631187 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.5572. Min Act: -0.1700
Data Index: 3878928 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.5572. Min Act: -0.1700
Data Index: 6306752 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.5259. Min Act: -0.1700
Data Index: 2154672 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.5259. Min Act: -0.1700
Data Index: 4246661 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.5259. Min Act: -0.1700
Data Index: 6275298 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.4947. Min Act: -0.1700
Data Index: 1412877 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9009. Min Range: -6.9009
Max Act: 6.4634. Min Act: -0.1700
Data Index: 43303 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19