Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 424 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4275. Min Range: -8.4275
Max Act: 8.4275. Min Act: -0.1700
Data Index: 4379362 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.7400. Min Act: -0.1700
Data Index: 6357127 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.5525. Min Act: -0.1700
Data Index: 3432640 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.4275. Min Act: -0.1700
Data Index: 2200196 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.4900. Min Act: -0.1700
Data Index: 3453120 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.2400. Min Act: -0.1700
Data Index: 3690014 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.2713. Min Act: -0.1700
Data Index: 5284860 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.2088. Min Act: -0.1700
Data Index: 5677296 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.1775. Min Act: -0.1700
Data Index: 629615 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.1150. Min Act: -0.1700
Data Index: 3233167 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.1463. Min Act: -0.1700
Data Index: 8411052 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.0525. Min Act: -0.1700
Data Index: 1269353 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.1150. Min Act: -0.1700
Data Index: 2900405 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.1463. Min Act: -0.1700
Data Index: 8573770 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.0838. Min Act: -0.1700
Data Index: 4161319 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4275. Min Range: -8.4275
Max Act: 6.9900. Min Act: -0.1700
Data Index: 7220213 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4275. Min Range: -8.4275
Max Act: 7.0213. Min Act: -0.1700
Data Index: 3526768 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4275. Min Range: -8.4275
Max Act: 6.8650. Min Act: -0.1700
Data Index: 6949589 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4275. Min Range: -8.4275
Max Act: 6.9275. Min Act: -0.1700
Data Index: 3209914 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4275. Min Range: -8.4275
Max Act: 6.9588. Min Act: -0.1700
Data Index: 1490984 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19