Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3926 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.4229. Min Act: -0.1700
Data Index: 7350721 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.4066. Min Act: -0.1700
Data Index: 624261 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.3740. Min Act: -0.1700
Data Index: 4614666 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.3412. Min Act: -0.1700
Data Index: 7013124 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.3412. Min Act: -0.1700
Data Index: 5357100 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.3412. Min Act: -0.1700
Data Index: 2359860 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.3084. Min Act: -0.1700
Data Index: 8432563 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.3084. Min Act: -0.1700
Data Index: 8432566 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.2919. Min Act: -0.1700
Data Index: 3030109 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.2590. Min Act: -0.1700
Data Index: 7541175 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.2424. Min Act: -0.1700
Data Index: 7581860 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.2424. Min Act: -0.1700
Data Index: 607765 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.2590. Min Act: -0.1700
Data Index: 8273125 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.2424. Min Act: -0.1700
Data Index: 4568066 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.2424. Min Act: -0.1700
Data Index: 8610342 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.2424. Min Act: -0.1700
Data Index: 6163976 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.2259. Min Act: -0.1700
Data Index: 6912972 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.2093. Min Act: -0.1700
Data Index: 7933916 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.2259. Min Act: -0.1700
Data Index: 8432560 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4229. Min Range: -2.4229
Max Act: 2.1927. Min Act: -0.1700
Data Index: 5478002 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19