Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2100 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.9846. Min Act: -0.1700
Data Index: 6533093 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.9221. Min Act: -0.1700
Data Index: 1915481 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.9221. Min Act: -0.1700
Data Index: 6533096 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.8596. Min Act: -0.1700
Data Index: 4811042 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.8596. Min Act: -0.1700
Data Index: 8395460 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.8596. Min Act: -0.1700
Data Index: 2069711 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.8596. Min Act: -0.1700
Data Index: 8056121 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.8596. Min Act: -0.1700
Data Index: 7144656 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.8596. Min Act: -0.1699
Data Index: 2513271 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7971. Min Act: -0.1700
Data Index: 1667823 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7346. Min Act: -0.1700
Data Index: 3255348 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7346. Min Act: -0.1700
Data Index: 4811043 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7971. Min Act: -0.1700
Data Index: 2787390 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7971. Min Act: -0.1700
Data Index: 3367642 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7971. Min Act: -0.1700
Data Index: 654738 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7971. Min Act: -0.1700
Data Index: 4304205 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7346. Min Act: -0.1700
Data Index: 2364218 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7346. Min Act: -0.1700
Data Index: 812267 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7346. Min Act: -0.1700
Data Index: 1286137 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.6721. Min Act: -0.1700
Data Index: 3315453 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19