Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5182 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.3846. Min Act: -0.1700
Data Index: 4193752 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.2596. Min Act: -0.1700
Data Index: 4979201 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.1971. Min Act: -0.1700
Data Index: 6787042 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.1971. Min Act: -0.1700
Data Index: 1367052 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.1346. Min Act: -0.1700
Data Index: 715539 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.1346. Min Act: -0.1700
Data Index: 2180988 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.1033. Min Act: -0.1700
Data Index: 4945012 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.1033. Min Act: -0.1700
Data Index: 2773074 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.1346. Min Act: -0.1700
Data Index: 661456 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.1033. Min Act: -0.1700
Data Index: 7598013 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.0721. Min Act: -0.1700
Data Index: 1103397 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.0721. Min Act: -0.1700
Data Index: 8668953 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.0721. Min Act: -0.1700
Data Index: 6368193 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.1033. Min Act: -0.1700
Data Index: 4895663 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.0408. Min Act: -0.1700
Data Index: 3422465 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.0408. Min Act: -0.1700
Data Index: 235958 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.0408. Min Act: -0.1700
Data Index: 2940740 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.0408. Min Act: -0.1700
Data Index: 6665581 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3846. Min Range: -6.3846
Max Act: 5.9783. Min Act: -0.1700
Data Index: 3956906 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3846. Min Range: -6.3846
Max Act: 6.0096. Min Act: -0.1700
Data Index: 2646493 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19