Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3763 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5143. Min Range: -6.5143
Max Act: 6.5143. Min Act: -0.1700
Data Index: 2356715 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5143. Min Range: -6.5143
Max Act: 6.2643. Min Act: -0.1700
Data Index: 5366571 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5143. Min Range: -6.5143
Max Act: 6.1706. Min Act: -0.1700
Data Index: 1423941 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5143. Min Range: -6.5143
Max Act: 6.1706. Min Act: -0.1700
Data Index: 1807735 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5143. Min Range: -6.5143
Max Act: 6.1393. Min Act: -0.1700
Data Index: 8200122 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5143. Min Range: -6.5143
Max Act: 6.1393. Min Act: -0.1700
Data Index: 2092182 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5143. Min Range: -6.5143
Max Act: 6.1081. Min Act: -0.1700
Data Index: 1294071 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5143. Min Range: -6.5143
Max Act: 6.1393. Min Act: -0.1700
Data Index: 5807183 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5143. Min Range: -6.5143
Max Act: 6.0456. Min Act: -0.1700
Data Index: 2621997 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5143. Min Range: -6.5143
Max Act: 6.0456. Min Act: -0.1700
Data Index: 11052 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5143. Min Range: -6.5143
Max Act: 6.0456. Min Act: -0.1700
Data Index: 954748 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5143. Min Range: -6.5143
Max Act: 6.0143. Min Act: -0.1700
Data Index: 8772781 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5143. Min Range: -6.5143
Max Act: 6.0143. Min Act: -0.1700
Data Index: 475739 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5143. Min Range: -6.5143
Max Act: 5.9831. Min Act: -0.1700
Data Index: 2937291 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5143. Min Range: -6.5143
Max Act: 5.9831. Min Act: -0.1700
Data Index: 8610966 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5143. Min Range: -6.5143
Max Act: 5.9831. Min Act: -0.1700
Data Index: 8561149 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5143. Min Range: -6.5143
Max Act: 5.9831. Min Act: -0.1700
Data Index: 7257145 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5143. Min Range: -6.5143
Max Act: 5.9518. Min Act: -0.1700
Data Index: 4150556 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5143. Min Range: -6.5143
Max Act: 5.9206. Min Act: -0.1700
Data Index: 3731441 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5143. Min Range: -6.5143
Max Act: 5.9206. Min Act: -0.1700
Data Index: 5569932 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19