Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4983 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.3748. Min Act: -0.1700
Data Index: 7590901 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.3748. Min Act: -0.1700
Data Index: 7483137 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.3435. Min Act: -0.1700
Data Index: 5020537 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.3123. Min Act: -0.1700
Data Index: 4442690 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.2810. Min Act: -0.1700
Data Index: 4862817 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.2810. Min Act: -0.1700
Data Index: 6421167 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.2810. Min Act: -0.1700
Data Index: 1373981 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.2810. Min Act: -0.1700
Data Index: 1307744 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.2810. Min Act: -0.1700
Data Index: 6655099 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.2185. Min Act: -0.1700
Data Index: 8347227 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.2498. Min Act: -0.1700
Data Index: 2788883 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.2498. Min Act: -0.1700
Data Index: 6474338 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.2810. Min Act: -0.1700
Data Index: 1195312 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.2185. Min Act: -0.1700
Data Index: 3725407 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.2185. Min Act: -0.1700
Data Index: 6197201 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.2185. Min Act: -0.1700
Data Index: 3465999 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.2498. Min Act: -0.1700
Data Index: 1260904 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.1873. Min Act: -0.1700
Data Index: 446132 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.2185. Min Act: -0.1700
Data Index: 4684996 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3748. Min Range: -4.3748
Max Act: 4.1873. Min Act: -0.1700
Data Index: 6863315 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19