Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2387 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3293. Min Range: -6.3293
Max Act: 6.3293. Min Act: -0.1700
Data Index: 7387367 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3293. Min Range: -6.3293
Max Act: 6.1106. Min Act: -0.1700
Data Index: 6771312 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3293. Min Range: -6.3293
Max Act: 6.0793. Min Act: -0.1700
Data Index: 2349366 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.9856. Min Act: -0.1700
Data Index: 1007099 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.9543. Min Act: -0.1700
Data Index: 4018592 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.8293. Min Act: -0.1700
Data Index: 3408531 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.8606. Min Act: -0.1700
Data Index: 2199625 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.8606. Min Act: -0.1700
Data Index: 4403447 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.8606. Min Act: -0.1700
Data Index: 7565070 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.8606. Min Act: -0.1700
Data Index: 5776273 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.7981. Min Act: -0.1700
Data Index: 960992 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.7668. Min Act: -0.1700
Data Index: 7739281 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.7668. Min Act: -0.1700
Data Index: 7692005 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.7668. Min Act: -0.1700
Data Index: 7204806 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.7668. Min Act: -0.1700
Data Index: 1680748 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.7668. Min Act: -0.1700
Data Index: 7173086 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.7668. Min Act: -0.1700
Data Index: 3434919 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.7356. Min Act: -0.1700
Data Index: 1188040 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.7043. Min Act: -0.1700
Data Index: 732771 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3293. Min Range: -6.3293
Max Act: 5.7043. Min Act: -0.1700
Data Index: 6487473 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19