Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5807 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.4237. Min Act: -0.1700
Data Index: 7539761 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.4237. Min Act: -0.1700
Data Index: 7993945 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.3300. Min Act: -0.1700
Data Index: 1937864 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.2987. Min Act: -0.1700
Data Index: 4896746 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.2675. Min Act: -0.1700
Data Index: 5930961 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.1737. Min Act: -0.1700
Data Index: 556379 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.1425. Min Act: -0.1700
Data Index: 7093903 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.1112. Min Act: -0.1700
Data Index: 1656536 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.1112. Min Act: -0.1700
Data Index: 4526033 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.1112. Min Act: -0.1700
Data Index: 3618780 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.0800. Min Act: -0.1700
Data Index: 2728103 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.0800. Min Act: -0.1700
Data Index: 315736 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.0800. Min Act: -0.1700
Data Index: 4633829 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.0487. Min Act: -0.1700
Data Index: 7462922 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.0487. Min Act: -0.1700
Data Index: 1157427 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.0175. Min Act: -0.1700
Data Index: 7576902 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4237. Min Range: -6.4237
Max Act: 5.9862. Min Act: -0.1700
Data Index: 1382100 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4237. Min Range: -6.4237
Max Act: 6.0175. Min Act: -0.1700
Data Index: 1058499 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4237. Min Range: -6.4237
Max Act: 5.9862. Min Act: -0.1700
Data Index: 7232894 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4237. Min Range: -6.4237
Max Act: 5.9550. Min Act: -0.1700
Data Index: 8444622 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19