Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3601 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.3595. Min Act: -0.1700
Data Index: 3940922 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.2657. Min Act: -0.1700
Data Index: 4387546 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.2032. Min Act: -0.1700
Data Index: 6297131 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.1720. Min Act: -0.1700
Data Index: 5173920 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.1720. Min Act: -0.1700
Data Index: 8737775 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.1095. Min Act: -0.1700
Data Index: 4952850 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.0782. Min Act: -0.1700
Data Index: 6707272 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.1095. Min Act: -0.1700
Data Index: 5981907 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.0782. Min Act: -0.1700
Data Index: 8594319 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.0470. Min Act: -0.1700
Data Index: 6950160 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.0782. Min Act: -0.1700
Data Index: 4576404 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.0470. Min Act: -0.1700
Data Index: 6650988 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.0470. Min Act: -0.1700
Data Index: 7843792 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.0157. Min Act: -0.1700
Data Index: 3965059 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3595. Min Range: -5.3595
Max Act: 5.0157. Min Act: -0.1700
Data Index: 1156858 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3595. Min Range: -5.3595
Max Act: 4.9845. Min Act: -0.1700
Data Index: 1780722 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3595. Min Range: -5.3595
Max Act: 4.9845. Min Act: -0.1700
Data Index: 1617516 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3595. Min Range: -5.3595
Max Act: 4.9845. Min Act: -0.1700
Data Index: 3027157 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3595. Min Range: -5.3595
Max Act: 4.9845. Min Act: -0.1700
Data Index: 2064880 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3595. Min Range: -5.3595
Max Act: 4.9845. Min Act: -0.1700
Data Index: 3481520 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19