Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 576 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1369. Min Range: -4.1369
Max Act: 4.1369. Min Act: -0.1700
Data Index: 5412693 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1369. Min Range: -4.1369
Max Act: 4.1369. Min Act: -0.1700
Data Index: 467133 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1369. Min Range: -4.1369
Max Act: 4.1057. Min Act: -0.1700
Data Index: 446218 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1369. Min Range: -4.1369
Max Act: 4.0744. Min Act: -0.1700
Data Index: 314743 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1369. Min Range: -4.1369
Max Act: 4.0744. Min Act: -0.1700
Data Index: 3784222 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1369. Min Range: -4.1369
Max Act: 4.0432. Min Act: -0.1700
Data Index: 1073363 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1369. Min Range: -4.1369
Max Act: 4.0744. Min Act: -0.1700
Data Index: 8534134 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1369. Min Range: -4.1369
Max Act: 4.0432. Min Act: -0.1700
Data Index: 3912183 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1369. Min Range: -4.1369
Max Act: 4.0119. Min Act: -0.1700
Data Index: 6200735 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1369. Min Range: -4.1369
Max Act: 4.0119. Min Act: -0.1700
Data Index: 4890005 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1369. Min Range: -4.1369
Max Act: 4.0432. Min Act: -0.1700
Data Index: 950367 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1369. Min Range: -4.1369
Max Act: 3.9806. Min Act: -0.1700
Data Index: 5462770 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1369. Min Range: -4.1369
Max Act: 3.9494. Min Act: -0.1700
Data Index: 6702232 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1369. Min Range: -4.1369
Max Act: 3.9494. Min Act: -0.1700
Data Index: 1122675 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1369. Min Range: -4.1369
Max Act: 3.9494. Min Act: -0.1700
Data Index: 1150317 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1369. Min Range: -4.1369
Max Act: 3.8868. Min Act: -0.1700
Data Index: 1162851 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1369. Min Range: -4.1369
Max Act: 3.8868. Min Act: -0.1700
Data Index: 3518414 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1369. Min Range: -4.1369
Max Act: 3.8556. Min Act: -0.1700
Data Index: 2402050 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1369. Min Range: -4.1369
Max Act: 3.8868. Min Act: -0.1700
Data Index: 5223603 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1369. Min Range: -4.1369
Max Act: 3.9181. Min Act: -0.1700
Data Index: 3746104 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19