Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1993 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.6807. Min Act: -0.1700
Data Index: 7132796 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.5557. Min Act: -0.1700
Data Index: 7840530 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.5557. Min Act: -0.1700
Data Index: 650523 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.4619. Min Act: -0.1700
Data Index: 3026407 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.4307. Min Act: -0.1700
Data Index: 26118 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.3994. Min Act: -0.1700
Data Index: 8021179 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.3994. Min Act: -0.1700
Data Index: 5112792 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.3682. Min Act: -0.1700
Data Index: 177162 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.3682. Min Act: -0.1700
Data Index: 4865612 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.3369. Min Act: -0.1700
Data Index: 2100858 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.3369. Min Act: -0.1700
Data Index: 4919743 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.3057. Min Act: -0.1700
Data Index: 2932075 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.3057. Min Act: -0.1700
Data Index: 1282122 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.3057. Min Act: -0.1700
Data Index: 5134570 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.2432. Min Act: -0.1700
Data Index: 61660 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.2432. Min Act: -0.1700
Data Index: 286676 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.2119. Min Act: -0.1700
Data Index: 2670002 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.2119. Min Act: -0.1700
Data Index: 3988484 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.2119. Min Act: -0.1700
Data Index: 6475402 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6807. Min Range: -5.6807
Max Act: 5.2432. Min Act: -0.1700
Data Index: 7977047 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19