Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4284 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1850. Min Range: -8.1850
Max Act: 8.1850. Min Act: -0.1700
Data Index: 5107048 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.9663. Min Act: -0.1700
Data Index: 3432484 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.7475. Min Act: -0.1700
Data Index: 1881919 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.7163. Min Act: -0.1700
Data Index: 6406671 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.6538. Min Act: -0.1700
Data Index: 1285908 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.6225. Min Act: -0.1700
Data Index: 2373656 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.5600. Min Act: -0.1700
Data Index: 3584988 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.5913. Min Act: -0.1700
Data Index: 4401444 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.5600. Min Act: -0.1700
Data Index: 913336 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.4975. Min Act: -0.1700
Data Index: 4550147 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.4663. Min Act: -0.1700
Data Index: 6147521 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.4663. Min Act: -0.1700
Data Index: 5973750 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.4350. Min Act: -0.1700
Data Index: 1516331 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.4350. Min Act: -0.1700
Data Index: 7155467 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.4038. Min Act: -0.1700
Data Index: 6241270 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.3725. Min Act: -0.1700
Data Index: 8548922 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.3413. Min Act: -0.1700
Data Index: 4822532 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.3413. Min Act: -0.1700
Data Index: 5352461 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.3100. Min Act: -0.1700
Data Index: 530145 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1850. Min Range: -8.1850
Max Act: 7.3100. Min Act: -0.1700
Data Index: 8757002 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19