Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2196 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1377. Min Range: -5.1377
Max Act: 5.1377. Min Act: -0.1700
Data Index: 5880916 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1377. Min Range: -5.1377
Max Act: 5.0752. Min Act: -0.1700
Data Index: 628161 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1377. Min Range: -5.1377
Max Act: 5.1377. Min Act: -0.1700
Data Index: 2978529 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1377. Min Range: -5.1377
Max Act: 5.0127. Min Act: -0.1700
Data Index: 4645293 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1377. Min Range: -5.1377
Max Act: 5.0752. Min Act: -0.1700
Data Index: 2748994 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1377. Min Range: -5.1377
Max Act: 5.0752. Min Act: -0.1700
Data Index: 5142060 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1377. Min Range: -5.1377
Max Act: 5.0752. Min Act: -0.1700
Data Index: 5407810 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1377. Min Range: -5.1377
Max Act: 4.9814. Min Act: -0.1700
Data Index: 5688230 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1377. Min Range: -5.1377
Max Act: 5.0127. Min Act: -0.1700
Data Index: 683609 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1377. Min Range: -5.1377
Max Act: 4.9814. Min Act: -0.1700
Data Index: 7532281 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1377. Min Range: -5.1377
Max Act: 5.0439. Min Act: -0.1700
Data Index: 4128508 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1377. Min Range: -5.1377
Max Act: 4.9814. Min Act: -0.1700
Data Index: 473169 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1377. Min Range: -5.1377
Max Act: 4.9814. Min Act: -0.1700
Data Index: 5629097 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1377. Min Range: -5.1377
Max Act: 4.8877. Min Act: -0.1700
Data Index: 6692121 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1377. Min Range: -5.1377
Max Act: 4.9502. Min Act: -0.1700
Data Index: 7092638 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1377. Min Range: -5.1377
Max Act: 4.9814. Min Act: -0.1700
Data Index: 280078 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1377. Min Range: -5.1377
Max Act: 4.9502. Min Act: -0.1700
Data Index: 8377288 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1377. Min Range: -5.1377
Max Act: 5.0127. Min Act: -0.1700
Data Index: 2831926 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1377. Min Range: -5.1377
Max Act: 4.9502. Min Act: -0.1700
Data Index: 4727193 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1377. Min Range: -5.1377
Max Act: 4.9189. Min Act: -0.1700
Data Index: 2842575 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19