Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4095 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.9392. Min Act: -0.1700
Data Index: 7002008 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.8455. Min Act: -0.1700
Data Index: 1285648 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.6267. Min Act: -0.1700
Data Index: 7800985 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.5017. Min Act: -0.1700
Data Index: 932134 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.3142. Min Act: -0.1700
Data Index: 2763048 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.3142. Min Act: -0.1700
Data Index: 8605675 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.3142. Min Act: -0.1700
Data Index: 1828309 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.3142. Min Act: -0.1700
Data Index: 892897 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.2517. Min Act: -0.1700
Data Index: 2207196 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.2517. Min Act: -0.1700
Data Index: 5723698 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.2517. Min Act: -0.1700
Data Index: 8224950 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.2205. Min Act: -0.1700
Data Index: 3818294 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.1892. Min Act: -0.1700
Data Index: 7423061 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.1892. Min Act: -0.1700
Data Index: 8529458 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.2205. Min Act: -0.1700
Data Index: 5826131 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.1892. Min Act: -0.1700
Data Index: 3619656 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.1892. Min Act: -0.1700
Data Index: 5475066 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.1892. Min Act: -0.1700
Data Index: 667896 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.1580. Min Act: -0.1700
Data Index: 7519812 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9392. Min Range: -5.9392
Max Act: 5.1892. Min Act: -0.1700
Data Index: 7109673 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19