Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5473 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1551. Min Range: -6.1551
Max Act: 6.1551. Min Act: -0.1700
Data Index: 4282681 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.9364. Min Act: -0.1700
Data Index: 8467401 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.9364. Min Act: -0.1700
Data Index: 6906631 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8114. Min Act: -0.1700
Data Index: 1417855 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7801. Min Act: -0.1700
Data Index: 5093622 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8114. Min Act: -0.1700
Data Index: 7477032 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7801. Min Act: -0.1700
Data Index: 5834259 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7489. Min Act: -0.1700
Data Index: 5633353 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7489. Min Act: -0.1700
Data Index: 7272923 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7489. Min Act: -0.1700
Data Index: 6762640 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7801. Min Act: -0.1700
Data Index: 3889208 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7489. Min Act: -0.1700
Data Index: 5333603 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7489. Min Act: -0.1700
Data Index: 7294936 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7176. Min Act: -0.1700
Data Index: 4843800 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7176. Min Act: -0.1700
Data Index: 8056636 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6864. Min Act: -0.1700
Data Index: 6812576 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6864. Min Act: -0.1700
Data Index: 4308618 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6551. Min Act: -0.1700
Data Index: 4608925 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6551. Min Act: -0.1700
Data Index: 6806299 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6239. Min Act: -0.1700
Data Index: 2844906 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19