Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4784 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.6959. Min Act: -0.1700
Data Index: 6592645 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.6022. Min Act: -0.1700
Data Index: 6878012 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.5709. Min Act: -0.1700
Data Index: 4727360 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.4772. Min Act: -0.1700
Data Index: 5744455 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.3834. Min Act: -0.1700
Data Index: 8479371 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.3522. Min Act: -0.1700
Data Index: 6635783 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.3209. Min Act: -0.1700
Data Index: 1094087 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.3209. Min Act: -0.1700
Data Index: 3500561 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.3209. Min Act: -0.1700
Data Index: 7039445 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.3209. Min Act: -0.1700
Data Index: 7154067 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.3209. Min Act: -0.1700
Data Index: 5830264 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.2584. Min Act: -0.1700
Data Index: 2048519 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.2584. Min Act: -0.1700
Data Index: 7839731 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.2584. Min Act: -0.1700
Data Index: 1818156 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.1959. Min Act: -0.1700
Data Index: 3782190 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.2272. Min Act: -0.1700
Data Index: 6534694 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.2272. Min Act: -0.1700
Data Index: 4842678 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.2272. Min Act: -0.1700
Data Index: 7204072 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.1959. Min Act: -0.1700
Data Index: 1522791 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6959. Min Range: -4.6959
Max Act: 4.1959. Min Act: -0.1700
Data Index: 5215703 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19