Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5645 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5604. Min Range: -6.5604
Max Act: 6.5604. Min Act: -0.1700
Data Index: 2298240 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5604. Min Range: -6.5604
Max Act: 6.3104. Min Act: -0.1700
Data Index: 5885699 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5604. Min Range: -6.5604
Max Act: 6.2167. Min Act: -0.1700
Data Index: 4003078 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5604. Min Range: -6.5604
Max Act: 6.1854. Min Act: -0.1700
Data Index: 361876 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5604. Min Range: -6.5604
Max Act: 6.1542. Min Act: -0.1700
Data Index: 4958867 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5604. Min Range: -6.5604
Max Act: 6.1229. Min Act: -0.1700
Data Index: 5946770 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5604. Min Range: -6.5604
Max Act: 6.1229. Min Act: -0.1700
Data Index: 550642 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5604. Min Range: -6.5604
Max Act: 6.0292. Min Act: -0.1700
Data Index: 1871059 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5604. Min Range: -6.5604
Max Act: 5.9979. Min Act: -0.1700
Data Index: 6126565 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5604. Min Range: -6.5604
Max Act: 5.9979. Min Act: -0.1700
Data Index: 5528495 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5604. Min Range: -6.5604
Max Act: 5.9979. Min Act: -0.1700
Data Index: 8726858 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5604. Min Range: -6.5604
Max Act: 5.9667. Min Act: -0.1700
Data Index: 137344 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5604. Min Range: -6.5604
Max Act: 5.9354. Min Act: -0.1700
Data Index: 6408437 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5604. Min Range: -6.5604
Max Act: 5.9042. Min Act: -0.1700
Data Index: 1143267 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5604. Min Range: -6.5604
Max Act: 5.9354. Min Act: -0.1700
Data Index: 377037 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5604. Min Range: -6.5604
Max Act: 5.9354. Min Act: -0.1700
Data Index: 7657960 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5604. Min Range: -6.5604
Max Act: 5.9042. Min Act: -0.1700
Data Index: 4733287 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5604. Min Range: -6.5604
Max Act: 5.8729. Min Act: -0.1700
Data Index: 5866566 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5604. Min Range: -6.5604
Max Act: 5.9042. Min Act: -0.1700
Data Index: 5817895 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5604. Min Range: -6.5604
Max Act: 5.9042. Min Act: -0.1700
Data Index: 1145204 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19