Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5305 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0625. Min Range: -10.0625
Max Act: 10.0625. Min Act: -0.1700
Data Index: 7731841 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.9375. Min Act: -0.1700
Data Index: 8612007 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.8125. Min Act: -0.1700
Data Index: 2740926 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.7500. Min Act: -0.1700
Data Index: 3663305 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.5625. Min Act: -0.1700
Data Index: 7477254 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.5625. Min Act: -0.1700
Data Index: 5336175 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.5625. Min Act: -0.1700
Data Index: 2231255 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.5000. Min Act: -0.1700
Data Index: 3377812 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.4375. Min Act: -0.1700
Data Index: 7583456 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.4375. Min Act: -0.1700
Data Index: 386228 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.4375. Min Act: -0.1700
Data Index: 6432746 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.4375. Min Act: -0.1700
Data Index: 1958765 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.4375. Min Act: -0.1700
Data Index: 4027167 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.4375. Min Act: -0.1700
Data Index: 2805571 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.4375. Min Act: -0.1700
Data Index: 2703484 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.3750. Min Act: -0.1700
Data Index: 6242569 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.3125. Min Act: -0.1700
Data Index: 3463521 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.3125. Min Act: -0.1700
Data Index: 1000614 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.3125. Min Act: -0.1700
Data Index: 3318070 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0625. Min Range: -10.0625
Max Act: 9.3125. Min Act: -0.1700
Data Index: 4683283 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19