Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1675 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.5756. Min Act: -0.1700
Data Index: 5805720 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.3256. Min Act: -0.1700
Data Index: 2313612 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.2943. Min Act: -0.1700
Data Index: 2690882 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.2318. Min Act: -0.1700
Data Index: 1324821 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.2943. Min Act: -0.1700
Data Index: 1226187 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.2006. Min Act: -0.1700
Data Index: 7352950 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.2631. Min Act: -0.1700
Data Index: 5275610 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.2006. Min Act: -0.1700
Data Index: 5262268 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.2318. Min Act: -0.1700
Data Index: 2752701 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.2006. Min Act: -0.1700
Data Index: 743564 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.2318. Min Act: -0.1700
Data Index: 7326253 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.1693. Min Act: -0.1700
Data Index: 4150074 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.2006. Min Act: -0.1700
Data Index: 4902172 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.2006. Min Act: -0.1700
Data Index: 5404582 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.2006. Min Act: -0.1700
Data Index: 5181822 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.1693. Min Act: -0.1700
Data Index: 3496316 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.2006. Min Act: -0.1700
Data Index: 8111254 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.1693. Min Act: -0.1700
Data Index: 4297437 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.1381. Min Act: -0.1700
Data Index: 83299 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5756. Min Range: -5.5756
Max Act: 5.2006. Min Act: -0.1700
Data Index: 6381354 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19