Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6354 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.9160. Min Act: -0.1700
Data Index: 1543047 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.7910. Min Act: -0.1700
Data Index: 1602590 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.7285. Min Act: -0.1700
Data Index: 4700587 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.6660. Min Act: -0.1700
Data Index: 6674921 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.5410. Min Act: -0.1700
Data Index: 4656299 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.5410. Min Act: -0.1700
Data Index: 8721716 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.4785. Min Act: -0.1700
Data Index: 1250787 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.4785. Min Act: -0.1700
Data Index: 3095970 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.4160. Min Act: -0.1700
Data Index: 392668 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.4160. Min Act: -0.1700
Data Index: 8644383 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.2910. Min Act: -0.1700
Data Index: 2773886 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.2285. Min Act: -0.1700
Data Index: 3031021 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.1660. Min Act: -0.1700
Data Index: 389366 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.2285. Min Act: -0.1700
Data Index: 1826217 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.2285. Min Act: -0.1700
Data Index: 7171500 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.1660. Min Act: -0.1700
Data Index: 5654099 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.1660. Min Act: -0.1700
Data Index: 4653988 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.1660. Min Act: -0.1700
Data Index: 4514862 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.1035. Min Act: -0.1700
Data Index: 1408887 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9160. Min Range: -8.9160
Max Act: 8.1035. Min Act: -0.1700
Data Index: 456031 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19