Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4018 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.3752. Min Act: -0.1700
Data Index: 1812124 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.3752. Min Act: -0.1700
Data Index: 1772231 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.3752. Min Act: -0.1700
Data Index: 6627794 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.3440. Min Act: -0.1700
Data Index: 3186130 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.3440. Min Act: -0.1700
Data Index: 540615 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.3440. Min Act: -0.1700
Data Index: 1812125 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.3127. Min Act: -0.1700
Data Index: 4048302 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.2815. Min Act: -0.1700
Data Index: 8630457 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.2502. Min Act: -0.1700
Data Index: 7379998 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.2815. Min Act: -0.1700
Data Index: 3127589 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.2815. Min Act: -0.1700
Data Index: 5087103 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.2815. Min Act: -0.1700
Data Index: 1472428 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.2190. Min Act: -0.1700
Data Index: 4332447 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.1877. Min Act: -0.1700
Data Index: 3824060 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.1877. Min Act: -0.1700
Data Index: 4539355 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.1877. Min Act: -0.1700
Data Index: 8787619 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.1877. Min Act: -0.1700
Data Index: 7380000 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.1877. Min Act: -0.1700
Data Index: 5424483 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.1565. Min Act: -0.1700
Data Index: 1310829 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3752. Min Range: -5.3752
Max Act: 5.1565. Min Act: -0.1700
Data Index: 4903716 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19