Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3971 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1585. Min Range: -6.1585
Max Act: 6.1585. Min Act: -0.1700
Data Index: 6057813 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.9398. Min Act: -0.1700
Data Index: 5708089 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.8460. Min Act: -0.1700
Data Index: 8056397 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.8148. Min Act: -0.1700
Data Index: 8149414 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.8148. Min Act: -0.1700
Data Index: 650532 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.8460. Min Act: -0.1700
Data Index: 540448 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.7835. Min Act: -0.1700
Data Index: 3794002 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.6898. Min Act: -0.1700
Data Index: 2261039 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.6898. Min Act: -0.1700
Data Index: 2971593 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.6898. Min Act: -0.1700
Data Index: 207899 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.6898. Min Act: -0.1700
Data Index: 3405299 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.6898. Min Act: -0.1700
Data Index: 5055186 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.6273. Min Act: -0.1700
Data Index: 3199952 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.6273. Min Act: -0.1700
Data Index: 4181884 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.6273. Min Act: -0.1700
Data Index: 4191657 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.6273. Min Act: -0.1700
Data Index: 6436879 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.6273. Min Act: -0.1700
Data Index: 5721649 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.6273. Min Act: -0.1700
Data Index: 3682891 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.5960. Min Act: -0.1700
Data Index: 3297188 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1585. Min Range: -6.1585
Max Act: 5.5960. Min Act: -0.1700
Data Index: 5068077 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19