Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2743 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.8638. Min Act: -0.1700
Data Index: 5565311 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.8326. Min Act: -0.1700
Data Index: 751610 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.7388. Min Act: -0.1700
Data Index: 8545859 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.7388. Min Act: -0.1700
Data Index: 7473439 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.6763. Min Act: -0.1700
Data Index: 1606606 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.7076. Min Act: -0.1700
Data Index: 7535478 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.7076. Min Act: -0.1700
Data Index: 5311452 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.6763. Min Act: -0.1700
Data Index: 3194469 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.6763. Min Act: -0.1700
Data Index: 5717923 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.6451. Min Act: -0.1700
Data Index: 3487066 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.6451. Min Act: -0.1700
Data Index: 5896177 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5826. Min Act: -0.1700
Data Index: 6544478 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.6138. Min Act: -0.1700
Data Index: 130521 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5201. Min Act: -0.1700
Data Index: 6464606 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5513. Min Act: -0.1700
Data Index: 794640 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5513. Min Act: -0.1700
Data Index: 4731144 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5513. Min Act: -0.1700
Data Index: 2220622 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5201. Min Act: -0.1700
Data Index: 4541520 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4888. Min Act: -0.1700
Data Index: 4038280 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5201. Min Act: -0.1700
Data Index: 7668194 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19