Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6996. Min Act: -0.1700
Data Index: 4567236 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5900. Min Act: -0.1700
Data Index: 3358698 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.4961. Min Act: -0.1700
Data Index: 6905222 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.4961. Min Act: -0.1700
Data Index: 7211916 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.4491. Min Act: -0.1700
Data Index: 5289302 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.4491. Min Act: -0.1700
Data Index: 5606388 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.4491. Min Act: -0.1700
Data Index: 7705849 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.4334. Min Act: -0.1700
Data Index: 7703859 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.4334. Min Act: -0.1700
Data Index: 8461837 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.4177. Min Act: -0.1700
Data Index: 7110644 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.4021. Min Act: -0.1700
Data Index: 3379723 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.3864. Min Act: -0.1700
Data Index: 2348833 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.4021. Min Act: -0.1700
Data Index: 7213554 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.4021. Min Act: -0.1700
Data Index: 6470552 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.4021. Min Act: -0.1700
Data Index: 7665899 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.3864. Min Act: -0.1700
Data Index: 600393 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.3864. Min Act: -0.1700
Data Index: 2936477 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.3864. Min Act: -0.1700
Data Index: 1400868 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.3864. Min Act: -0.1700
Data Index: 2772046 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.3707. Min Act: -0.1700
Data Index: 767350 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19