Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 347 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5780. Min Range: -8.5780
Max Act: 8.5780. Min Act: -0.1700
Data Index: 8665570 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5780. Min Range: -8.5780
Max Act: 8.2655. Min Act: -0.1700
Data Index: 2747498 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5780. Min Range: -8.5780
Max Act: 8.2030. Min Act: -0.1700
Data Index: 756839 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5780. Min Range: -8.5780
Max Act: 8.2030. Min Act: -0.1700
Data Index: 7372083 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5780. Min Range: -8.5780
Max Act: 8.1405. Min Act: -0.1700
Data Index: 2074034 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5780. Min Range: -8.5780
Max Act: 8.1405. Min Act: -0.1700
Data Index: 3299068 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5780. Min Range: -8.5780
Max Act: 8.1405. Min Act: -0.1700
Data Index: 5427024 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5780. Min Range: -8.5780
Max Act: 8.0155. Min Act: -0.1700
Data Index: 2626239 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5780. Min Range: -8.5780
Max Act: 8.0155. Min Act: -0.1700
Data Index: 8743292 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5780. Min Range: -8.5780
Max Act: 7.9530. Min Act: -0.1700
Data Index: 4031266 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5780. Min Range: -8.5780
Max Act: 7.9530. Min Act: -0.1700
Data Index: 8448062 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5780. Min Range: -8.5780
Max Act: 7.9530. Min Act: -0.1700
Data Index: 2030866 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5780. Min Range: -8.5780
Max Act: 7.9217. Min Act: -0.1700
Data Index: 4058140 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5780. Min Range: -8.5780
Max Act: 7.9530. Min Act: -0.1700
Data Index: 995922 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5780. Min Range: -8.5780
Max Act: 7.8280. Min Act: -0.1700
Data Index: 467855 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5780. Min Range: -8.5780
Max Act: 7.8592. Min Act: -0.1700
Data Index: 7249720 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5780. Min Range: -8.5780
Max Act: 7.7967. Min Act: -0.1700
Data Index: 2148333 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5780. Min Range: -8.5780
Max Act: 7.7967. Min Act: -0.1700
Data Index: 4265521 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5780. Min Range: -8.5780
Max Act: 7.8280. Min Act: -0.1700
Data Index: 5784176 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5780. Min Range: -8.5780
Max Act: 7.7967. Min Act: -0.1700
Data Index: 6124258 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19