Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2673 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.8150. Min Act: -0.1700
Data Index: 7195851 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.7193. Min Act: -0.1700
Data Index: 1593599 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.6552. Min Act: -0.1700
Data Index: 3624658 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.6070. Min Act: -0.1700
Data Index: 682894 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.6070. Min Act: -0.1700
Data Index: 6320820 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.5748. Min Act: -0.1700
Data Index: 8496313 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.5909. Min Act: -0.1700
Data Index: 5624679 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.5587. Min Act: -0.1700
Data Index: 7490229 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.6070. Min Act: -0.1700
Data Index: 8553801 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.5748. Min Act: -0.1700
Data Index: 170391 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.5587. Min Act: -0.1700
Data Index: 5901989 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.5748. Min Act: -0.1700
Data Index: 5519517 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.5587. Min Act: -0.1700
Data Index: 7416673 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.5748. Min Act: -0.1700
Data Index: 7149395 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.5425. Min Act: -0.1700
Data Index: 2556007 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.5264. Min Act: -0.1700
Data Index: 497165 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.5425. Min Act: -0.1700
Data Index: 7116335 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.5587. Min Act: -0.1700
Data Index: 3431793 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.5425. Min Act: -0.1700
Data Index: 6623236 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8150. Min Range: -2.8150
Max Act: 2.5264. Min Act: -0.1700
Data Index: 6361100 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19