Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3119 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.8812. Min Act: -0.1700
Data Index: 7454059 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.8187. Min Act: -0.1700
Data Index: 7454057 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.6937. Min Act: -0.1700
Data Index: 2659987 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.6937. Min Act: -0.1700
Data Index: 4619392 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.6312. Min Act: -0.1700
Data Index: 5911074 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.5062. Min Act: -0.1700
Data Index: 5120630 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.5062. Min Act: -0.1700
Data Index: 7209915 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.4437. Min Act: -0.1700
Data Index: 5073216 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.3187. Min Act: -0.1700
Data Index: 6101253 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.3812. Min Act: -0.1700
Data Index: 1418654 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.4437. Min Act: -0.1700
Data Index: 2749745 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.3187. Min Act: -0.1700
Data Index: 2200659 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.3187. Min Act: -0.1700
Data Index: 5352129 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.2562. Min Act: -0.1700
Data Index: 4714413 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.2562. Min Act: -0.1700
Data Index: 7592944 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.3187. Min Act: -0.1700
Data Index: 4146947 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.1312. Min Act: -0.1700
Data Index: 3592059 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.1937. Min Act: -0.1700
Data Index: 7188235 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.1312. Min Act: -0.1700
Data Index: 7188231 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8812. Min Range: -8.8812
Max Act: 8.0687. Min Act: -0.1700
Data Index: 5307084 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19