Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 424 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.9416. Min Act: -0.1700
Data Index: 3075003 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.8478. Min Act: -0.1700
Data Index: 1569618 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.8478. Min Act: -0.1700
Data Index: 5991943 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.8478. Min Act: -0.1700
Data Index: 4600593 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.7853. Min Act: -0.1700
Data Index: 6969232 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.8166. Min Act: -0.1700
Data Index: 4115079 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.8166. Min Act: -0.1700
Data Index: 3231604 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.8166. Min Act: -0.1700
Data Index: 5708334 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.7853. Min Act: -0.1700
Data Index: 1891320 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.7853. Min Act: -0.1700
Data Index: 7070631 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.7541. Min Act: -0.1700
Data Index: 8442227 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.7541. Min Act: -0.1700
Data Index: 6696345 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.7541. Min Act: -0.1700
Data Index: 5308791 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.7541. Min Act: -0.1700
Data Index: 3876924 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.7541. Min Act: -0.1700
Data Index: 2186496 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.7228. Min Act: -0.1700
Data Index: 4354611 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.7228. Min Act: -0.1700
Data Index: 6617361 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.7228. Min Act: -0.1700
Data Index: 5873996 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.7228. Min Act: -0.1700
Data Index: 1716869 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9416. Min Range: -5.9416
Max Act: 5.7228. Min Act: -0.1700
Data Index: 3397621 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19