Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5026 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0691. Min Range: -5.0691
Max Act: 5.0691. Min Act: -0.1700
Data Index: 5886244 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.8191. Min Act: -0.1700
Data Index: 3973127 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.6628. Min Act: -0.1700
Data Index: 2637817 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.6003. Min Act: -0.1700
Data Index: 2146050 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.5691. Min Act: -0.1700
Data Index: 1922968 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.5378. Min Act: -0.1700
Data Index: 4877684 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.5378. Min Act: -0.1700
Data Index: 6418255 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.5066. Min Act: -0.1700
Data Index: 4818302 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.5066. Min Act: -0.1700
Data Index: 5551813 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.5066. Min Act: -0.1700
Data Index: 464275 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.4753. Min Act: -0.1700
Data Index: 2863898 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.4441. Min Act: -0.1700
Data Index: 6524697 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.4441. Min Act: -0.1700
Data Index: 438767 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.4441. Min Act: -0.1700
Data Index: 8202534 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.3816. Min Act: -0.1700
Data Index: 5804797 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.4128. Min Act: -0.1700
Data Index: 405697 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.4128. Min Act: -0.1700
Data Index: 1819395 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.4128. Min Act: -0.1700
Data Index: 8212880 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.3816. Min Act: -0.1700
Data Index: 3128124 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0691. Min Range: -5.0691
Max Act: 4.3816. Min Act: -0.1700
Data Index: 1734930 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19