Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 884 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.4340. Min Act: -0.1700
Data Index: 3330768 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.3715. Min Act: -0.1700
Data Index: 2332616 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.3402. Min Act: -0.1700
Data Index: 1192018 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.3090. Min Act: -0.1700
Data Index: 715168 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.3090. Min Act: -0.1700
Data Index: 4303205 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.2777. Min Act: -0.1700
Data Index: 4315014 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.2152. Min Act: -0.1700
Data Index: 1069719 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.1840. Min Act: -0.1700
Data Index: 5675556 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.1215. Min Act: -0.1700
Data Index: 4931645 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.0902. Min Act: -0.1700
Data Index: 8001193 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.0590. Min Act: -0.1700
Data Index: 4116120 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.0590. Min Act: -0.1700
Data Index: 5315615 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4340. Min Range: -6.4340
Max Act: 5.9965. Min Act: -0.1700
Data Index: 7770471 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.0277. Min Act: -0.1700
Data Index: 7706027 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.0277. Min Act: -0.1700
Data Index: 849760 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4340. Min Range: -6.4340
Max Act: 6.0277. Min Act: -0.1700
Data Index: 8292145 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4340. Min Range: -6.4340
Max Act: 5.9965. Min Act: -0.1700
Data Index: 3405355 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4340. Min Range: -6.4340
Max Act: 5.9965. Min Act: -0.1700
Data Index: 581595 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4340. Min Range: -6.4340
Max Act: 5.9965. Min Act: -0.1700
Data Index: 5840020 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4340. Min Range: -6.4340
Max Act: 5.9965. Min Act: -0.1700
Data Index: 6826100 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19