Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 174 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.9658. Min Act: -0.1700
Data Index: 1233934 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.8408. Min Act: -0.1700
Data Index: 3877908 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.8096. Min Act: -0.1700
Data Index: 3265001 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.7783. Min Act: -0.1700
Data Index: 6938023 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.6221. Min Act: -0.1700
Data Index: 2763331 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.5908. Min Act: -0.1700
Data Index: 478137 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.5908. Min Act: -0.1700
Data Index: 6749536 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.5908. Min Act: -0.1700
Data Index: 5336595 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.5908. Min Act: -0.1700
Data Index: 1515459 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.5283. Min Act: -0.1700
Data Index: 3681764 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.5283. Min Act: -0.1700
Data Index: 3932572 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.5283. Min Act: -0.1700
Data Index: 1713241 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.5283. Min Act: -0.1700
Data Index: 6515582 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.4971. Min Act: -0.1700
Data Index: 8171073 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.4971. Min Act: -0.1700
Data Index: 8171085 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.5283. Min Act: -0.1700
Data Index: 2323160 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.4971. Min Act: -0.1700
Data Index: 8675730 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.4971. Min Act: -0.1700
Data Index: 5780986 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.4971. Min Act: -0.1700
Data Index: 54849 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9658. Min Range: -4.9658
Max Act: 4.4658. Min Act: -0.1700
Data Index: 4946695 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19