Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4368 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.9905. Min Act: -0.1700
Data Index: 18563 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.9280. Min Act: -0.1700
Data Index: 3128618 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7718. Min Act: -0.1700
Data Index: 1382442 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7718. Min Act: -0.1700
Data Index: 5275850 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.5218. Min Act: -0.1700
Data Index: 7215432 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.4905. Min Act: -0.1700
Data Index: 7442734 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.4593. Min Act: -0.1700
Data Index: 8776394 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.4280. Min Act: -0.1700
Data Index: 1976609 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.3655. Min Act: -0.1700
Data Index: 369955 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.3655. Min Act: -0.1700
Data Index: 3049375 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.3655. Min Act: -0.1700
Data Index: 5402308 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.3343. Min Act: -0.1700
Data Index: 2440063 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.3030. Min Act: -0.1700
Data Index: 3337863 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.3030. Min Act: -0.1700
Data Index: 1491737 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.3030. Min Act: -0.1700
Data Index: 7048978 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.2718. Min Act: -0.1700
Data Index: 4105320 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.2405. Min Act: -0.1700
Data Index: 2654183 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.2405. Min Act: -0.1700
Data Index: 4566427 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.2405. Min Act: -0.1700
Data Index: 3400097 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.2093. Min Act: -0.1700
Data Index: 8629902 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19