Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3192 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0547. Min Range: -5.0547
Max Act: 5.0547. Min Act: -0.1700
Data Index: 2046451 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.8672. Min Act: -0.1700
Data Index: 3650931 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.8672. Min Act: -0.1700
Data Index: 4423665 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.8360. Min Act: -0.1700
Data Index: 3983830 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.8360. Min Act: -0.1700
Data Index: 1086729 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.8360. Min Act: -0.1700
Data Index: 7437785 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.8047. Min Act: -0.1700
Data Index: 22783 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.8360. Min Act: -0.1700
Data Index: 428270 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.7735. Min Act: -0.1700
Data Index: 22785 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.7422. Min Act: -0.1700
Data Index: 1308060 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.7422. Min Act: -0.1700
Data Index: 75132 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.7422. Min Act: -0.1700
Data Index: 1604968 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.7422. Min Act: -0.1700
Data Index: 3300399 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.7110. Min Act: -0.1700
Data Index: 8392006 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.7110. Min Act: -0.1700
Data Index: 7103634 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.6797. Min Act: -0.1700
Data Index: 22795 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.6485. Min Act: -0.1700
Data Index: 7170644 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.6485. Min Act: -0.1700
Data Index: 7639343 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.6172. Min Act: -0.1700
Data Index: 7602725 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0547. Min Range: -5.0547
Max Act: 4.6172. Min Act: -0.1700
Data Index: 3363096 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19