Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2368 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.8914. Min Act: -0.1700
Data Index: 4793603 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.8829. Min Act: -0.1700
Data Index: 7241048 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.8058. Min Act: -0.1700
Data Index: 8440455 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.8143. Min Act: -0.1700
Data Index: 8122238 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7885. Min Act: -0.1700
Data Index: 4176744 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7885. Min Act: -0.1700
Data Index: 6808434 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7885. Min Act: -0.1700
Data Index: 804441 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7799. Min Act: -0.1700
Data Index: 5111455 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7713. Min Act: -0.1700
Data Index: 8272111 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7627. Min Act: -0.1700
Data Index: 3757419 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7541. Min Act: -0.1700
Data Index: 1371978 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7627. Min Act: -0.1700
Data Index: 5888196 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7541. Min Act: -0.1700
Data Index: 1427895 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7368. Min Act: -0.1700
Data Index: 5586337 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7368. Min Act: -0.1700
Data Index: 8163048 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7368. Min Act: -0.1700
Data Index: 3983245 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7281. Min Act: -0.1700
Data Index: 2928116 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7454. Min Act: -0.1700
Data Index: 6133885 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7281. Min Act: -0.1700
Data Index: 7825798 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8914. Min Range: -1.8914
Max Act: 1.7368. Min Act: -0.1700
Data Index: 5323003 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19