Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4117 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.8048. Min Act: -0.1700
Data Index: 7032009 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.7110. Min Act: -0.1700
Data Index: 8573546 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.6173. Min Act: -0.1700
Data Index: 6596692 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.6173. Min Act: -0.1700
Data Index: 6135075 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.5860. Min Act: -0.1700
Data Index: 3392591 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.5860. Min Act: -0.1700
Data Index: 3249863 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.5860. Min Act: -0.1700
Data Index: 8262173 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.5860. Min Act: -0.1700
Data Index: 1635834 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.5860. Min Act: -0.1700
Data Index: 6093567 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.5548. Min Act: -0.1700
Data Index: 441224 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.5235. Min Act: -0.1700
Data Index: 5246940 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.5235. Min Act: -0.1700
Data Index: 5812019 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.4923. Min Act: -0.1700
Data Index: 6559049 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.4298. Min Act: -0.1700
Data Index: 5107624 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.4610. Min Act: -0.1700
Data Index: 6494341 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.4610. Min Act: -0.1700
Data Index: 730440 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.4610. Min Act: -0.1700
Data Index: 3642179 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.4923. Min Act: -0.1700
Data Index: 6484537 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.4298. Min Act: -0.1700
Data Index: 5083386 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8048. Min Range: -4.8048
Max Act: 4.4298. Min Act: -0.1700
Data Index: 1330328 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19