Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2351 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2413. Min Range: -10.2413
Max Act: 10.2413. Min Act: -0.1700
Data Index: 3753887 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2413. Min Range: -10.2413
Max Act: 10.2413. Min Act: -0.1700
Data Index: 3457215 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2413. Min Range: -10.2413
Max Act: 10.1163. Min Act: -0.1700
Data Index: 7233372 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2413. Min Range: -10.2413
Max Act: 10.1163. Min Act: -0.1700
Data Index: 8079148 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2413. Min Range: -10.2413
Max Act: 10.1788. Min Act: -0.1700
Data Index: 6192136 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2413. Min Range: -10.2413
Max Act: 10.1163. Min Act: -0.1700
Data Index: 6863530 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2413. Min Range: -10.2413
Max Act: 10.0538. Min Act: -0.1700
Data Index: 5471606 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2413. Min Range: -10.2413
Max Act: 9.9913. Min Act: -0.1700
Data Index: 1521730 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2413. Min Range: -10.2413
Max Act: 10.0538. Min Act: -0.1700
Data Index: 8418324 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2413. Min Range: -10.2413
Max Act: 9.9913. Min Act: -0.1700
Data Index: 3240591 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2413. Min Range: -10.2413
Max Act: 9.9913. Min Act: -0.1700
Data Index: 2315542 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2413. Min Range: -10.2413
Max Act: 9.9288. Min Act: -0.1700
Data Index: 7569972 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2413. Min Range: -10.2413
Max Act: 9.9913. Min Act: -0.1700
Data Index: 2190709 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2413. Min Range: -10.2413
Max Act: 9.8663. Min Act: -0.1700
Data Index: 399344 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2413. Min Range: -10.2413
Max Act: 9.8663. Min Act: -0.1700
Data Index: 3396488 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2413. Min Range: -10.2413
Max Act: 9.8663. Min Act: -0.1700
Data Index: 3738434 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2413. Min Range: -10.2413
Max Act: 9.9288. Min Act: -0.1700
Data Index: 1175294 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2413. Min Range: -10.2413
Max Act: 9.8038. Min Act: -0.1700
Data Index: 2822826 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2413. Min Range: -10.2413
Max Act: 9.8038. Min Act: -0.1700
Data Index: 5100933 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2413. Min Range: -10.2413
Max Act: 9.8038. Min Act: -0.1700
Data Index: 738961 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19