Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4537 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1119. Min Range: -5.1119
Max Act: 5.1119. Min Act: -0.1700
Data Index: 238984 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1119. Min Range: -5.1119
Max Act: 5.0182. Min Act: -0.1700
Data Index: 8197858 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1119. Min Range: -5.1119
Max Act: 5.0182. Min Act: -0.1700
Data Index: 206265 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.7369. Min Act: -0.1700
Data Index: 477755 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.7682. Min Act: -0.1700
Data Index: 6370061 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.7369. Min Act: -0.1700
Data Index: 7002467 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.6744. Min Act: -0.1700
Data Index: 5640553 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.6744. Min Act: -0.1700
Data Index: 4883617 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.6432. Min Act: -0.1700
Data Index: 3667000 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.6432. Min Act: -0.1700
Data Index: 5330573 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.6119. Min Act: -0.1700
Data Index: 2182227 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.6119. Min Act: -0.1700
Data Index: 1284047 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.6119. Min Act: -0.1700
Data Index: 8651796 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.5807. Min Act: -0.1700
Data Index: 891508 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.5807. Min Act: -0.1700
Data Index: 6984887 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.5807. Min Act: -0.1700
Data Index: 4732151 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.5807. Min Act: -0.1700
Data Index: 4207001 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.5807. Min Act: -0.1700
Data Index: 5904244 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.5807. Min Act: -0.1700
Data Index: 7002466 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1119. Min Range: -5.1119
Max Act: 4.5807. Min Act: -0.1700
Data Index: 4488938 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19