Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3605 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1074. Min Range: -6.1074
Max Act: 6.1074. Min Act: -0.1700
Data Index: 4502962 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.8261. Min Act: -0.1700
Data Index: 31422 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.8261. Min Act: -0.1700
Data Index: 2991309 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.7949. Min Act: -0.1700
Data Index: 3171934 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.7636. Min Act: -0.1700
Data Index: 1203857 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.7636. Min Act: -0.1700
Data Index: 5698952 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.7324. Min Act: -0.1700
Data Index: 7178106 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.7324. Min Act: -0.1700
Data Index: 8077786 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.6386. Min Act: -0.1700
Data Index: 6862988 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.6386. Min Act: -0.1700
Data Index: 1491219 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.5761. Min Act: -0.1700
Data Index: 2069821 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.5449. Min Act: -0.1700
Data Index: 4991562 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.5136. Min Act: -0.1700
Data Index: 4326073 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.5136. Min Act: -0.1700
Data Index: 2156480 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.4824. Min Act: -0.1700
Data Index: 1666322 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.4824. Min Act: -0.1700
Data Index: 2696460 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.4824. Min Act: -0.1700
Data Index: 237558 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.4199. Min Act: -0.1700
Data Index: 4896130 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.4511. Min Act: -0.1700
Data Index: 1595901 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1074. Min Range: -6.1074
Max Act: 5.4511. Min Act: -0.1700
Data Index: 3126693 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19