Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4695 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.7032. Min Act: -0.1700
Data Index: 4217885 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.7032. Min Act: -0.1700
Data Index: 7494047 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.6407. Min Act: -0.1700
Data Index: 2412529 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.5469. Min Act: -0.1700
Data Index: 4338484 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.5157. Min Act: -0.1700
Data Index: 3957126 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.5157. Min Act: -0.1700
Data Index: 1852034 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.4219. Min Act: -0.1700
Data Index: 2274785 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.3594. Min Act: -0.1700
Data Index: 5189383 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.3594. Min Act: -0.1700
Data Index: 4096379 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.3594. Min Act: -0.1700
Data Index: 7572420 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.3594. Min Act: -0.1700
Data Index: 2746675 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.3594. Min Act: -0.1700
Data Index: 2665002 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.2969. Min Act: -0.1700
Data Index: 5482556 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.2969. Min Act: -0.1700
Data Index: 6380922 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.2969. Min Act: -0.1700
Data Index: 8461738 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.2969. Min Act: -0.1700
Data Index: 3279707 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.2657. Min Act: -0.1700
Data Index: 6096835 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.2657. Min Act: -0.1700
Data Index: 1226587 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.2657. Min Act: -0.1700
Data Index: 6231412 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7032. Min Range: -6.7032
Max Act: 6.2344. Min Act: -0.1700
Data Index: 1878476 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19