Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.7752. Min Act: -0.1700
Data Index: 5800516 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.5877. Min Act: -0.1700
Data Index: 3898443 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.5252. Min Act: -0.1700
Data Index: 4904811 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.5252. Min Act: -0.1700
Data Index: 1367471 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.5252. Min Act: -0.1700
Data Index: 4868210 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.5252. Min Act: -0.1700
Data Index: 3101086 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.4627. Min Act: -0.1700
Data Index: 6378579 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.4314. Min Act: -0.1700
Data Index: 3361153 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.4002. Min Act: -0.1700
Data Index: 2918895 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.3064. Min Act: -0.1700
Data Index: 6146205 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.2752. Min Act: -0.1700
Data Index: 8473015 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.3064. Min Act: -0.1700
Data Index: 876517 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.2439. Min Act: -0.1700
Data Index: 5914373 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.2752. Min Act: -0.1700
Data Index: 7501681 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.2439. Min Act: -0.1700
Data Index: 2122970 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.2439. Min Act: -0.1700
Data Index: 2441400 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.2127. Min Act: -0.1700
Data Index: 1149751 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.2127. Min Act: -0.1700
Data Index: 3849179 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.1814. Min Act: -0.1700
Data Index: 7485763 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7752. Min Range: -7.7752
Max Act: 7.2439. Min Act: -0.1700
Data Index: 6707610 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19