Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2867 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.7904. Min Act: -0.1700
Data Index: 1739291 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.7592. Min Act: -0.1700
Data Index: 6944885 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.7592. Min Act: -0.1700
Data Index: 8820155 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.7279. Min Act: -0.1700
Data Index: 4482733 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6967. Min Act: -0.1700
Data Index: 2211180 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6967. Min Act: -0.1700
Data Index: 6267462 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6967. Min Act: -0.1700
Data Index: 5026425 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6967. Min Act: -0.1700
Data Index: 8132384 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6654. Min Act: -0.1700
Data Index: 5264819 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6967. Min Act: -0.1700
Data Index: 602801 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6654. Min Act: -0.1700
Data Index: 815034 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6654. Min Act: -0.1700
Data Index: 7746800 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6654. Min Act: -0.1700
Data Index: 8325690 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6342. Min Act: -0.1700
Data Index: 7960138 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6342. Min Act: -0.1700
Data Index: 2924966 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6029. Min Act: -0.1700
Data Index: 5821912 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6029. Min Act: -0.1700
Data Index: 6050818 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6342. Min Act: -0.1700
Data Index: 696521 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6029. Min Act: -0.1700
Data Index: 7560062 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7904. Min Range: -4.7904
Max Act: 4.6029. Min Act: -0.1700
Data Index: 3632837 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19