Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2882 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8690. Min Range: -7.8690
Max Act: 7.8690. Min Act: -0.1700
Data Index: 1944895 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8690. Min Range: -7.8690
Max Act: 7.6503. Min Act: -0.1700
Data Index: 3190761 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8690. Min Range: -7.8690
Max Act: 7.6190. Min Act: -0.1700
Data Index: 1823939 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8690. Min Range: -7.8690
Max Act: 7.2440. Min Act: -0.1700
Data Index: 6267638 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8690. Min Range: -7.8690
Max Act: 7.2128. Min Act: -0.1700
Data Index: 5324674 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8690. Min Range: -7.8690
Max Act: 7.1190. Min Act: -0.1700
Data Index: 6002903 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8690. Min Range: -7.8690
Max Act: 7.0565. Min Act: -0.1700
Data Index: 5860920 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8690. Min Range: -7.8690
Max Act: 7.0565. Min Act: -0.1700
Data Index: 111215 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8690. Min Range: -7.8690
Max Act: 6.9628. Min Act: -0.1700
Data Index: 2820791 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8690. Min Range: -7.8690
Max Act: 6.9003. Min Act: -0.1700
Data Index: 3897098 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8690. Min Range: -7.8690
Max Act: 6.8690. Min Act: -0.1700
Data Index: 8629221 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8690. Min Range: -7.8690
Max Act: 6.9003. Min Act: -0.1700
Data Index: 6118827 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8690. Min Range: -7.8690
Max Act: 6.8690. Min Act: -0.1700
Data Index: 7055502 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8690. Min Range: -7.8690
Max Act: 6.9003. Min Act: -0.1700
Data Index: 5940371 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8690. Min Range: -7.8690
Max Act: 6.8690. Min Act: -0.1700
Data Index: 8519655 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8690. Min Range: -7.8690
Max Act: 6.8378. Min Act: -0.1700
Data Index: 5452585 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8690. Min Range: -7.8690
Max Act: 6.8065. Min Act: -0.1700
Data Index: 7052951 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8690. Min Range: -7.8690
Max Act: 6.7753. Min Act: -0.1700
Data Index: 5046404 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8690. Min Range: -7.8690
Max Act: 6.7753. Min Act: -0.1700
Data Index: 1954781 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8690. Min Range: -7.8690
Max Act: 6.7440. Min Act: -0.1700
Data Index: 2133227 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19