Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2768 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.2325. Min Act: -0.1700
Data Index: 1100955 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.1075. Min Act: -0.1700
Data Index: 7219645 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0763. Min Act: -0.1700
Data Index: 444435 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0763. Min Act: -0.1700
Data Index: 6821851 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0450. Min Act: -0.1700
Data Index: 3691739 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0450. Min Act: -0.1700
Data Index: 890945 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0763. Min Act: -0.1699
Data Index: 2024916 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0450. Min Act: -0.1700
Data Index: 3450671 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2325. Min Range: -5.2325
Max Act: 4.9825. Min Act: -0.1700
Data Index: 4722274 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0138. Min Act: -0.1700
Data Index: 2756199 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0138. Min Act: -0.1700
Data Index: 3164629 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0138. Min Act: -0.1700
Data Index: 173930 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2325. Min Range: -5.2325
Max Act: 4.8888. Min Act: -0.1700
Data Index: 749724 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2325. Min Range: -5.2325
Max Act: 4.9200. Min Act: -0.1700
Data Index: 8211651 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2325. Min Range: -5.2325
Max Act: 4.9200. Min Act: -0.1700
Data Index: 6888668 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2325. Min Range: -5.2325
Max Act: 4.9200. Min Act: -0.1700
Data Index: 6080939 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2325. Min Range: -5.2325
Max Act: 4.9200. Min Act: -0.1700
Data Index: 8242820 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2325. Min Range: -5.2325
Max Act: 4.8888. Min Act: -0.1700
Data Index: 2383183 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2325. Min Range: -5.2325
Max Act: 4.8575. Min Act: -0.1700
Data Index: 1050581 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2325. Min Range: -5.2325
Max Act: 4.8575. Min Act: -0.1700
Data Index: 5477289 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19