Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4037 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.7604. Min Act: -0.1700
Data Index: 5767259 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.6667. Min Act: -0.1700
Data Index: 6875196 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.6042. Min Act: -0.1700
Data Index: 7167869 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.6042. Min Act: -0.1700
Data Index: 7452849 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.5729. Min Act: -0.1700
Data Index: 2467475 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.6042. Min Act: -0.1700
Data Index: 2886306 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.5729. Min Act: -0.1700
Data Index: 3702989 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.5729. Min Act: -0.1700
Data Index: 6619392 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.5104. Min Act: -0.1700
Data Index: 3719943 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.4792. Min Act: -0.1700
Data Index: 4479490 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.4479. Min Act: -0.1700
Data Index: 7905 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.4479. Min Act: -0.1700
Data Index: 4064909 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.4167. Min Act: -0.1700
Data Index: 3130481 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.4479. Min Act: -0.1700
Data Index: 8171218 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.4479. Min Act: -0.1700
Data Index: 1962286 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.4479. Min Act: -0.1700
Data Index: 250181 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.3854. Min Act: -0.1700
Data Index: 7226262 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.4167. Min Act: -0.1700
Data Index: 7701851 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.3854. Min Act: -0.1700
Data Index: 6745579 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7604. Min Range: -5.7604
Max Act: 5.2917. Min Act: -0.1700
Data Index: 1309847 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19