Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3620 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5439. Min Range: -7.5439
Max Act: 7.5439. Min Act: -0.1700
Data Index: 2584739 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5439. Min Range: -7.5439
Max Act: 7.1689. Min Act: -0.1700
Data Index: 5617201 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5439. Min Range: -7.5439
Max Act: 7.1377. Min Act: -0.1700
Data Index: 7790315 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5439. Min Range: -7.5439
Max Act: 7.0752. Min Act: -0.1700
Data Index: 5642910 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5439. Min Range: -7.5439
Max Act: 7.0752. Min Act: -0.1700
Data Index: 6469605 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5439. Min Range: -7.5439
Max Act: 7.0752. Min Act: -0.1700
Data Index: 8215109 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5439. Min Range: -7.5439
Max Act: 6.9814. Min Act: -0.1700
Data Index: 6619409 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5439. Min Range: -7.5439
Max Act: 6.9502. Min Act: -0.1700
Data Index: 6541682 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5439. Min Range: -7.5439
Max Act: 6.9502. Min Act: -0.1700
Data Index: 8705230 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5439. Min Range: -7.5439
Max Act: 6.9189. Min Act: -0.1700
Data Index: 7212989 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5439. Min Range: -7.5439
Max Act: 6.9502. Min Act: -0.1700
Data Index: 2242175 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5439. Min Range: -7.5439
Max Act: 6.8877. Min Act: -0.1700
Data Index: 5736034 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5439. Min Range: -7.5439
Max Act: 6.9189. Min Act: -0.1700
Data Index: 759057 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5439. Min Range: -7.5439
Max Act: 6.9189. Min Act: -0.1700
Data Index: 3342727 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5439. Min Range: -7.5439
Max Act: 6.9189. Min Act: -0.1700
Data Index: 8788953 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5439. Min Range: -7.5439
Max Act: 6.8877. Min Act: -0.1700
Data Index: 5359364 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5439. Min Range: -7.5439
Max Act: 6.8877. Min Act: -0.1700
Data Index: 1455860 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5439. Min Range: -7.5439
Max Act: 6.8877. Min Act: -0.1700
Data Index: 8370041 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5439. Min Range: -7.5439
Max Act: 6.8564. Min Act: -0.1700
Data Index: 7963356 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5439. Min Range: -7.5439
Max Act: 6.8564. Min Act: -0.1700
Data Index: 975020 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19