Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3712 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4881. Min Range: -8.4881
Max Act: 8.4881. Min Act: -0.1700
Data Index: 7218673 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4881. Min Range: -8.4881
Max Act: 8.1756. Min Act: -0.1700
Data Index: 8339365 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4881. Min Range: -8.4881
Max Act: 8.1756. Min Act: -0.1700
Data Index: 1886286 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4881. Min Range: -8.4881
Max Act: 8.1131. Min Act: -0.1700
Data Index: 7038909 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4881. Min Range: -8.4881
Max Act: 8.0506. Min Act: -0.1700
Data Index: 165815 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.9256. Min Act: -0.1700
Data Index: 876644 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.9881. Min Act: -0.1700
Data Index: 815787 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.8631. Min Act: -0.1700
Data Index: 4106923 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.8006. Min Act: -0.1700
Data Index: 1073190 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.8006. Min Act: -0.1700
Data Index: 7407830 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.8006. Min Act: -0.1700
Data Index: 4095620 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.7381. Min Act: -0.1700
Data Index: 7281743 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.7381. Min Act: -0.1700
Data Index: 612531 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.6756. Min Act: -0.1700
Data Index: 8734269 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.7381. Min Act: -0.1700
Data Index: 8418217 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.7381. Min Act: -0.1700
Data Index: 6977917 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.8006. Min Act: -0.1700
Data Index: 1737855 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.6756. Min Act: -0.1700
Data Index: 4399958 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.6756. Min Act: -0.1700
Data Index: 1675894 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4881. Min Range: -8.4881
Max Act: 7.6756. Min Act: -0.1700
Data Index: 3870991 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19