Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1357 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0023. Min Range: -8.0023
Max Act: 8.0023. Min Act: -0.1700
Data Index: 5823451 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.9398. Min Act: -0.1700
Data Index: 5812205 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.9398. Min Act: -0.1700
Data Index: 8147688 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.9398. Min Act: -0.1700
Data Index: 752212 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.9398. Min Act: -0.1700
Data Index: 692468 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.8773. Min Act: -0.1700
Data Index: 3530629 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.8773. Min Act: -0.1700
Data Index: 6065829 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.8148. Min Act: -0.1700
Data Index: 7906301 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.8148. Min Act: -0.1700
Data Index: 7158509 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.7523. Min Act: -0.1700
Data Index: 6088808 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.7523. Min Act: -0.1700
Data Index: 3679986 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.7523. Min Act: -0.1700
Data Index: 4139335 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.7523. Min Act: -0.1700
Data Index: 3029759 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.6898. Min Act: -0.1700
Data Index: 7153133 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.7210. Min Act: -0.1700
Data Index: 1404688 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.7210. Min Act: -0.1700
Data Index: 5847063 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.6898. Min Act: -0.1700
Data Index: 8047631 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.7210. Min Act: -0.1700
Data Index: 6126829 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.6898. Min Act: -0.1700
Data Index: 848283 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0023. Min Range: -8.0023
Max Act: 7.7210. Min Act: -0.1700
Data Index: 2953199 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19