Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0955. Min Range: -5.0955
Max Act: 5.0955. Min Act: -0.1700
Data Index: 4900697 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.8455. Min Act: -0.1700
Data Index: 1362943 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.7830. Min Act: -0.1700
Data Index: 4111149 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.6580. Min Act: -0.1700
Data Index: 1438614 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.5330. Min Act: -0.1700
Data Index: 2921760 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.5330. Min Act: -0.1700
Data Index: 5001674 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.5330. Min Act: -0.1700
Data Index: 387920 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.5017. Min Act: -0.1700
Data Index: 8818910 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.5017. Min Act: -0.1700
Data Index: 2491333 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.5330. Min Act: -0.1700
Data Index: 4682056 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.4705. Min Act: -0.1700
Data Index: 1489118 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.4392. Min Act: -0.1700
Data Index: 7477913 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.4705. Min Act: -0.1700
Data Index: 7811265 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.4392. Min Act: -0.1700
Data Index: 8818924 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.4080. Min Act: -0.1700
Data Index: 8009951 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.4392. Min Act: -0.1700
Data Index: 3544336 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.4080. Min Act: -0.1700
Data Index: 957010 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.4080. Min Act: -0.1700
Data Index: 2490641 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.4080. Min Act: -0.1700
Data Index: 8818905 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0955. Min Range: -5.0955
Max Act: 4.3767. Min Act: -0.1700
Data Index: 6774915 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19