Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3729 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 19.1937. Min Range: -19.1937
Max Act: 19.1937. Min Act: -0.1700
Data Index: 5016599 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 19.1937. Min Range: -19.1937
Max Act: 19.1937. Min Act: -0.1700
Data Index: 6531737 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 19.1937. Min Range: -19.1937
Max Act: 19.0687. Min Act: -0.1700
Data Index: 5995038 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.9437. Min Act: -0.1700
Data Index: 7894361 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.9437. Min Act: -0.1700
Data Index: 4950356 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.6937. Min Act: -0.1700
Data Index: 2313283 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.8187. Min Act: -0.1700
Data Index: 504621 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.6937. Min Act: -0.1700
Data Index: 6488678 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.6937. Min Act: -0.1700
Data Index: 5254434 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.5687. Min Act: -0.1700
Data Index: 1015319 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.5687. Min Act: -0.1700
Data Index: 3322743 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.6937. Min Act: -0.1700
Data Index: 8353375 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.5687. Min Act: -0.1700
Data Index: 3406187 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.6937. Min Act: -0.1700
Data Index: 2931411 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.4437. Min Act: -0.1700
Data Index: 4965593 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.4437. Min Act: -0.1700
Data Index: 309408 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.3187. Min Act: -0.1700
Data Index: 6473618 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.4437. Min Act: -0.1700
Data Index: 4222074 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.4437. Min Act: -0.1700
Data Index: 8485057 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 19.1937. Min Range: -19.1937
Max Act: 18.4437. Min Act: -0.1700
Data Index: 5759857 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19