Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3740 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.7190. Min Act: -0.1700
Data Index: 2058866 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.7190. Min Act: -0.1700
Data Index: 6470167 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.6565. Min Act: -0.1700
Data Index: 7862562 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.6565. Min Act: -0.1700
Data Index: 6226016 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.6565. Min Act: -0.1700
Data Index: 1353835 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.6252. Min Act: -0.1700
Data Index: 950692 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.5940. Min Act: -0.1700
Data Index: 7011400 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.5940. Min Act: -0.1700
Data Index: 4624664 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.5315. Min Act: -0.1700
Data Index: 1244806 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.5002. Min Act: -0.1700
Data Index: 7058990 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.4690. Min Act: -0.1700
Data Index: 3548471 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.4377. Min Act: -0.1700
Data Index: 3072337 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.4377. Min Act: -0.1700
Data Index: 2178035 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.4065. Min Act: -0.1700
Data Index: 1621729 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.3752. Min Act: -0.1700
Data Index: 7197129 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.3752. Min Act: -0.1700
Data Index: 5555734 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.3752. Min Act: -0.1700
Data Index: 4781123 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.3752. Min Act: -0.1700
Data Index: 4828381 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.3752. Min Act: -0.1700
Data Index: 1274551 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7190. Min Range: -5.7190
Max Act: 5.3752. Min Act: -0.1700
Data Index: 1933130 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19