Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 47 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.3761. Min Act: -0.1700
Data Index: 6687291 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.3136. Min Act: -0.1700
Data Index: 5234732 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.2823. Min Act: -0.1700
Data Index: 3936939 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.2511. Min Act: -0.1700
Data Index: 3563219 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.2198. Min Act: -0.1700
Data Index: 62644 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.2198. Min Act: -0.1700
Data Index: 2748523 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.1886. Min Act: -0.1700
Data Index: 1451267 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.1573. Min Act: -0.1700
Data Index: 7704150 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.1573. Min Act: -0.1700
Data Index: 7987252 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.1261. Min Act: -0.1700
Data Index: 2037504 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.1261. Min Act: -0.1700
Data Index: 2976789 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.0948. Min Act: -0.1700
Data Index: 3936618 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.0636. Min Act: -0.1700
Data Index: 6368405 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.0636. Min Act: -0.1700
Data Index: 2753478 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.0636. Min Act: -0.1700
Data Index: 1857838 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.0636. Min Act: -0.1700
Data Index: 2199173 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.0636. Min Act: -0.1700
Data Index: 2303709 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.0323. Min Act: -0.1700
Data Index: 5528213 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.0636. Min Act: -0.1700
Data Index: 5435079 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3761. Min Range: -5.3761
Max Act: 5.0636. Min Act: -0.1700
Data Index: 1636670 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19