Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3890 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.4460. Min Act: -0.1700
Data Index: 1728451 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.4460. Min Act: -0.1687
Data Index: 2983763 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.4196. Min Act: -0.1700
Data Index: 1932273 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.4196. Min Act: -0.1700
Data Index: 4840 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.3932. Min Act: -0.1608
Data Index: 6337783 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.4020. Min Act: -0.1700
Data Index: 2536846 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.4020. Min Act: -0.1700
Data Index: 4239008 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.3932. Min Act: -0.1700
Data Index: 4215286 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.3755. Min Act: -0.1697
Data Index: 3281005 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.3844. Min Act: -0.1700
Data Index: 2450959 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.3844. Min Act: -0.1700
Data Index: 7817593 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.3844. Min Act: -0.1700
Data Index: 4521690 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.3755. Min Act: -0.1699
Data Index: 6070690 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.3755. Min Act: -0.1700
Data Index: 5699727 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.3667. Min Act: -0.1700
Data Index: 4825744 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.3667. Min Act: -0.1696
Data Index: 3132499 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.3755. Min Act: -0.1698
Data Index: 6872811 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.3755. Min Act: -0.1696
Data Index: 5580370 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.3755. Min Act: -0.1700
Data Index: 3181536 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4460. Min Range: -1.4460
Max Act: 1.3667. Min Act: -0.1700
Data Index: 7309635 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19