Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3211 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.7628. Min Act: -0.1700
Data Index: 509147 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.6378. Min Act: -0.1700
Data Index: 2133331 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.5753. Min Act: -0.1700
Data Index: 7742358 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.5753. Min Act: -0.1700
Data Index: 5182869 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.5440. Min Act: -0.1700
Data Index: 509906 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.5128. Min Act: -0.1700
Data Index: 4951306 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.4503. Min Act: -0.1700
Data Index: 3162214 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.4503. Min Act: -0.1700
Data Index: 7047294 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.4190. Min Act: -0.1700
Data Index: 6988977 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.3565. Min Act: -0.1700
Data Index: 8300648 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.3565. Min Act: -0.1700
Data Index: 1015489 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.3565. Min Act: -0.1700
Data Index: 5434183 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.3565. Min Act: -0.1700
Data Index: 544754 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.3565. Min Act: -0.1700
Data Index: 6342871 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.3878. Min Act: -0.1700
Data Index: 6703250 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.3253. Min Act: -0.1700
Data Index: 5512208 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.3253. Min Act: -0.1700
Data Index: 837749 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.3253. Min Act: -0.1700
Data Index: 917210 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.3253. Min Act: -0.1700
Data Index: 8463939 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7628. Min Range: -6.7628
Max Act: 6.2628. Min Act: -0.1700
Data Index: 4206365 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19