Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5376 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.7727. Min Act: -0.1700
Data Index: 729723 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.7102. Min Act: -0.1700
Data Index: 886184 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.7102. Min Act: -0.1700
Data Index: 8086826 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.6790. Min Act: -0.1700
Data Index: 2811288 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.5227. Min Act: -0.1700
Data Index: 4748041 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.4915. Min Act: -0.1700
Data Index: 1587933 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.4602. Min Act: -0.1700
Data Index: 6971114 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.4602. Min Act: -0.1700
Data Index: 4000382 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.4290. Min Act: -0.1700
Data Index: 3613033 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.4290. Min Act: -0.1700
Data Index: 2703205 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.4290. Min Act: -0.1700
Data Index: 5747876 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.3665. Min Act: -0.1700
Data Index: 6426249 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.3665. Min Act: -0.1700
Data Index: 2979417 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.4290. Min Act: -0.1700
Data Index: 5980105 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.3977. Min Act: -0.1700
Data Index: 7094471 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.3665. Min Act: -0.1700
Data Index: 7421675 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.3665. Min Act: -0.1700
Data Index: 956917 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.3665. Min Act: -0.1700
Data Index: 4114175 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.3665. Min Act: -0.1700
Data Index: 6305281 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7727. Min Range: -5.7727
Max Act: 5.3352. Min Act: -0.1700
Data Index: 3613077 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19