Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2545 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.7030. Min Act: -0.1700
Data Index: 65063 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.7030. Min Act: -0.1700
Data Index: 2651956 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.6717. Min Act: -0.1700
Data Index: 4351756 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.6405. Min Act: -0.1700
Data Index: 2850888 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.6405. Min Act: -0.1700
Data Index: 1079813 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.6092. Min Act: -0.1700
Data Index: 309035 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.6092. Min Act: -0.1700
Data Index: 4437553 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.5780. Min Act: -0.1697
Data Index: 6619698 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.6092. Min Act: -0.1700
Data Index: 4570982 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.5780. Min Act: -0.1700
Data Index: 6390283 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.5780. Min Act: -0.1700
Data Index: 1471310 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.5780. Min Act: -0.1700
Data Index: 5727586 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.5780. Min Act: -0.1700
Data Index: 5490356 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.5780. Min Act: -0.1700
Data Index: 8039709 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.5780. Min Act: -0.1700
Data Index: 4875482 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.5780. Min Act: -0.1700
Data Index: 6563687 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.5467. Min Act: -0.1700
Data Index: 712507 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.5467. Min Act: -0.1700
Data Index: 3749496 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.5155. Min Act: -0.1700
Data Index: 4512579 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7030. Min Range: -4.7030
Max Act: 4.5155. Min Act: -0.1700
Data Index: 1630692 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19