Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2907 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2096. Min Range: -5.2096
Max Act: 5.2096. Min Act: -0.1700
Data Index: 8206564 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.8971. Min Act: -0.1700
Data Index: 5661063 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.8346. Min Act: -0.1700
Data Index: 8391918 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.8659. Min Act: -0.1700
Data Index: 1210934 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.8346. Min Act: -0.1700
Data Index: 5229122 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.8034. Min Act: -0.1700
Data Index: 7138527 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.8034. Min Act: -0.1700
Data Index: 2900028 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.7721. Min Act: -0.1700
Data Index: 7915070 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.8034. Min Act: -0.1700
Data Index: 34556 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.7721. Min Act: -0.1700
Data Index: 4322191 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.7721. Min Act: -0.1700
Data Index: 1813056 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.7409. Min Act: -0.1700
Data Index: 2496720 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.7409. Min Act: -0.1700
Data Index: 5604844 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.7096. Min Act: -0.1700
Data Index: 8658853 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.7096. Min Act: -0.1700
Data Index: 7434126 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.7096. Min Act: -0.1700
Data Index: 4860711 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.7096. Min Act: -0.1700
Data Index: 2211874 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.7096. Min Act: -0.1700
Data Index: 6231453 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.7096. Min Act: -0.1700
Data Index: 6736267 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.6471. Min Act: -0.1700
Data Index: 1117213 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19