Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1946 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1340. Min Range: -8.1340
Max Act: 8.1340. Min Act: -0.1700
Data Index: 6742712 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1340. Min Range: -8.1340
Max Act: 8.0090. Min Act: -0.1700
Data Index: 2237352 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1340. Min Range: -8.1340
Max Act: 8.0090. Min Act: -0.1700
Data Index: 8315168 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.8840. Min Act: -0.1700
Data Index: 2499386 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.8840. Min Act: -0.1700
Data Index: 8450946 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.8840. Min Act: -0.1700
Data Index: 7698801 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.7590. Min Act: -0.1700
Data Index: 5512349 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.7590. Min Act: -0.1700
Data Index: 6397436 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.8215. Min Act: -0.1700
Data Index: 871749 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.7590. Min Act: -0.1700
Data Index: 755402 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.6340. Min Act: -0.1700
Data Index: 722824 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.6340. Min Act: -0.1700
Data Index: 4943130 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.6965. Min Act: -0.1699
Data Index: 3952625 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.6340. Min Act: -0.1700
Data Index: 2975344 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.6340. Min Act: -0.1700
Data Index: 8041465 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.6340. Min Act: -0.1700
Data Index: 2664704 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.6340. Min Act: -0.1700
Data Index: 6968961 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.6340. Min Act: -0.1700
Data Index: 2913367 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.5715. Min Act: -0.1700
Data Index: 1750687 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1340. Min Range: -8.1340
Max Act: 7.5715. Min Act: -0.1699
Data Index: 796007 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19