Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5401 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.3405. Min Act: -0.1698
Data Index: 7460593 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2780. Min Act: -0.1700
Data Index: 5496011 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2467. Min Act: -0.1700
Data Index: 7388771 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2467. Min Act: -0.1700
Data Index: 2874772 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1842. Min Act: -0.1700
Data Index: 8190945 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2155. Min Act: -0.1700
Data Index: 3473242 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2155. Min Act: -0.1700
Data Index: 1360064 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1842. Min Act: -0.1700
Data Index: 8302807 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1842. Min Act: -0.1700
Data Index: 2641673 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1842. Min Act: -0.1700
Data Index: 8080009 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1530. Min Act: -0.1699
Data Index: 4219641 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 3555947 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1530. Min Act: -0.1700
Data Index: 8637461 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1530. Min Act: -0.1700
Data Index: 2493958 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1530. Min Act: -0.1700
Data Index: 1946342 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1530. Min Act: -0.1700
Data Index: 889561 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1530. Min Act: -0.1699
Data Index: 6701254 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 4215308 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 2795813 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0905. Min Act: -0.1700
Data Index: 8339002 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19