Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2020 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.5582. Min Act: -0.1700
Data Index: 235838 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.4610. Min Act: -0.1700
Data Index: 6065477 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3795. Min Act: -0.1700
Data Index: 7172052 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.4122. Min Act: -0.1700
Data Index: 7017250 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3632. Min Act: -0.1700
Data Index: 4004495 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3795. Min Act: -0.1700
Data Index: 7778064 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3632. Min Act: -0.1700
Data Index: 8819626 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3632. Min Act: -0.1700
Data Index: 1684054 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3632. Min Act: -0.1700
Data Index: 8757233 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3632. Min Act: -0.1700
Data Index: 1901645 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3468. Min Act: -0.1700
Data Index: 4154164 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3632. Min Act: -0.1700
Data Index: 2962005 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3304. Min Act: -0.1700
Data Index: 8068641 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3304. Min Act: -0.1700
Data Index: 3622273 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3304. Min Act: -0.1700
Data Index: 3652966 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3304. Min Act: -0.1700
Data Index: 8630901 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3304. Min Act: -0.1700
Data Index: 1102011 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.2811. Min Act: -0.1700
Data Index: 5346723 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3304. Min Act: -0.1700
Data Index: 5353022 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5582. Min Range: -2.5582
Max Act: 2.3140. Min Act: -0.1700
Data Index: 8388030 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19