Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2253 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.2984. Min Act: -0.1700
Data Index: 3490145 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.2984. Min Act: -0.1700
Data Index: 6239851 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.2359. Min Act: -0.1700
Data Index: 7914579 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.2046. Min Act: -0.1700
Data Index: 2164196 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.2046. Min Act: -0.1700
Data Index: 271816 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.2046. Min Act: -0.1700
Data Index: 7712684 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.2046. Min Act: -0.1700
Data Index: 3215699 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1109. Min Act: -0.1700
Data Index: 5552785 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1421. Min Act: -0.1700
Data Index: 7361717 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1421. Min Act: -0.1700
Data Index: 3528796 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1421. Min Act: -0.1700
Data Index: 2243283 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1734. Min Act: -0.1700
Data Index: 8773096 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1109. Min Act: -0.1700
Data Index: 285724 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.0796. Min Act: -0.1700
Data Index: 6838308 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1109. Min Act: -0.1700
Data Index: 6172950 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1109. Min Act: -0.1700
Data Index: 3408801 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.0483. Min Act: -0.1700
Data Index: 7419391 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.0796. Min Act: -0.1700
Data Index: 6166905 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.0796. Min Act: -0.1700
Data Index: 4115733 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.0796. Min Act: -0.1700
Data Index: 7744868 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19