Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3044 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.8695. Min Act: -0.1700
Data Index: 5649146 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.8377. Min Act: -0.1700
Data Index: 5632139 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.8059. Min Act: -0.1700
Data Index: 8262836 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.7261. Min Act: -0.1700
Data Index: 2086947 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6781. Min Act: -0.1700
Data Index: 745792 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6941. Min Act: -0.1700
Data Index: 7990896 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6781. Min Act: -0.1700
Data Index: 5505419 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6941. Min Act: -0.1700
Data Index: 1775884 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.7101. Min Act: -0.1700
Data Index: 5355829 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6781. Min Act: -0.1700
Data Index: 7243274 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6781. Min Act: -0.1700
Data Index: 5777563 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6781. Min Act: -0.1700
Data Index: 2001826 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6781. Min Act: -0.1700
Data Index: 1136384 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6300. Min Act: -0.1700
Data Index: 3437158 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6300. Min Act: -0.1700
Data Index: 7670181 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6781. Min Act: -0.1700
Data Index: 4300487 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6460. Min Act: -0.1700
Data Index: 4025043 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6139. Min Act: -0.1700
Data Index: 1195177 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6460. Min Act: -0.1700
Data Index: 3352638 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8695. Min Range: -2.8695
Max Act: 2.6139. Min Act: -0.1700
Data Index: 5227155 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19