Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2811 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1997. Min Range: -7.1997
Max Act: 7.1685. Min Act: -0.1700
Data Index: 1375655 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1997. Min Range: -7.1997
Max Act: 7.1997. Min Act: -0.1700
Data Index: 4722353 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1997. Min Range: -7.1997
Max Act: 7.1997. Min Act: -0.1700
Data Index: 3668518 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1997. Min Range: -7.1997
Max Act: 7.1685. Min Act: -0.1700
Data Index: 2268368 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1997. Min Range: -7.1997
Max Act: 7.0747. Min Act: -0.1700
Data Index: 7308119 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1997. Min Range: -7.1997
Max Act: 7.0747. Min Act: -0.1700
Data Index: 5062336 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1997. Min Range: -7.1997
Max Act: 7.0747. Min Act: -0.1700
Data Index: 8527729 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1997. Min Range: -7.1997
Max Act: 7.0122. Min Act: -0.1700
Data Index: 5940960 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1997. Min Range: -7.1997
Max Act: 7.0122. Min Act: -0.1700
Data Index: 2348340 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1997. Min Range: -7.1997
Max Act: 6.9185. Min Act: -0.1700
Data Index: 2025728 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1997. Min Range: -7.1997
Max Act: 6.8872. Min Act: -0.1700
Data Index: 550797 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1997. Min Range: -7.1997
Max Act: 6.9497. Min Act: -0.1700
Data Index: 140305 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1997. Min Range: -7.1997
Max Act: 6.8560. Min Act: -0.1700
Data Index: 32857 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1997. Min Range: -7.1997
Max Act: 6.8872. Min Act: -0.1700
Data Index: 6755518 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1997. Min Range: -7.1997
Max Act: 6.8247. Min Act: -0.1700
Data Index: 5961007 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1997. Min Range: -7.1997
Max Act: 6.8872. Min Act: -0.1700
Data Index: 5080878 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1997. Min Range: -7.1997
Max Act: 6.8560. Min Act: -0.1700
Data Index: 2377182 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1997. Min Range: -7.1997
Max Act: 6.8872. Min Act: -0.1700
Data Index: 7767691 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1997. Min Range: -7.1997
Max Act: 6.8247. Min Act: -0.1700
Data Index: 5449974 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1997. Min Range: -7.1997
Max Act: 6.7935. Min Act: -0.1700
Data Index: 6847990 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19