Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5308 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.8160. Min Act: -0.1700
Data Index: 2532021 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.7535. Min Act: -0.1700
Data Index: 7254764 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.5035. Min Act: -0.1700
Data Index: 3100090 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.3785. Min Act: -0.1700
Data Index: 7598952 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.3160. Min Act: -0.1700
Data Index: 1201757 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.2535. Min Act: -0.1700
Data Index: 6596463 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.1910. Min Act: -0.1700
Data Index: 2159235 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.1910. Min Act: -0.1700
Data Index: 3670527 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.1910. Min Act: -0.1700
Data Index: 6221395 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.0660. Min Act: -0.1700
Data Index: 6182657 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.0035. Min Act: -0.1699
Data Index: 5475984 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8160. Min Range: -9.8160
Max Act: 8.9410. Min Act: -0.1700
Data Index: 5123923 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.0035. Min Act: -0.1700
Data Index: 8422744 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.0035. Min Act: -0.1700
Data Index: 4043596 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.0035. Min Act: -0.1700
Data Index: 8074732 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8160. Min Range: -9.8160
Max Act: 8.9410. Min Act: -0.1700
Data Index: 4396200 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8160. Min Range: -9.8160
Max Act: 8.9410. Min Act: -0.1700
Data Index: 6809570 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8160. Min Range: -9.8160
Max Act: 9.0035. Min Act: -0.1700
Data Index: 3369530 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8160. Min Range: -9.8160
Max Act: 8.9410. Min Act: -0.1700
Data Index: 6478174 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8160. Min Range: -9.8160
Max Act: 8.8785. Min Act: -0.1700
Data Index: 2634730 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19