Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1752. Min Range: -5.1752
Max Act: 5.1752. Min Act: -0.1700
Data Index: 1976732 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1752. Min Range: -5.1752
Max Act: 5.1752. Min Act: -0.1700
Data Index: 6986992 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1752. Min Range: -5.1752
Max Act: 5.1127. Min Act: -0.1700
Data Index: 7218928 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1752. Min Range: -5.1752
Max Act: 5.0814. Min Act: -0.1700
Data Index: 6228846 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1752. Min Range: -5.1752
Max Act: 5.0502. Min Act: -0.1700
Data Index: 6721028 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1752. Min Range: -5.1752
Max Act: 5.0189. Min Act: -0.1700
Data Index: 575280 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1752. Min Range: -5.1752
Max Act: 5.0189. Min Act: -0.1700
Data Index: 7330724 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1752. Min Range: -5.1752
Max Act: 4.9877. Min Act: -0.1700
Data Index: 34949 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1752. Min Range: -5.1752
Max Act: 4.9564. Min Act: -0.1700
Data Index: 4603916 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1752. Min Range: -5.1752
Max Act: 4.9564. Min Act: -0.1700
Data Index: 6968346 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1752. Min Range: -5.1752
Max Act: 4.9564. Min Act: -0.1700
Data Index: 4910658 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1752. Min Range: -5.1752
Max Act: 4.9252. Min Act: -0.1700
Data Index: 196738 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1752. Min Range: -5.1752
Max Act: 4.9252. Min Act: -0.1700
Data Index: 2112243 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1752. Min Range: -5.1752
Max Act: 4.9252. Min Act: -0.1700
Data Index: 3846069 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1752. Min Range: -5.1752
Max Act: 4.9252. Min Act: -0.1700
Data Index: 8339021 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1752. Min Range: -5.1752
Max Act: 4.9252. Min Act: -0.1700
Data Index: 3141976 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1752. Min Range: -5.1752
Max Act: 4.8939. Min Act: -0.1700
Data Index: 1884684 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1752. Min Range: -5.1752
Max Act: 4.8939. Min Act: -0.1700
Data Index: 6878023 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1752. Min Range: -5.1752
Max Act: 4.8627. Min Act: -0.1700
Data Index: 1415837 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1752. Min Range: -5.1752
Max Act: 4.8314. Min Act: -0.1700
Data Index: 306343 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19