Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0504. Min Range: -5.0504
Max Act: 5.0504. Min Act: -0.1700
Data Index: 3926288 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.9879. Min Act: -0.1700
Data Index: 6440796 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.8942. Min Act: -0.1700
Data Index: 8470816 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.8317. Min Act: -0.1700
Data Index: 2571023 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.8317. Min Act: -0.1700
Data Index: 5517141 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.8004. Min Act: -0.1700
Data Index: 4058540 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.8004. Min Act: -0.1700
Data Index: 3995808 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.7692. Min Act: -0.1700
Data Index: 4982498 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.7379. Min Act: -0.1700
Data Index: 8542089 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.7379. Min Act: -0.1700
Data Index: 6569291 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.7067. Min Act: -0.1700
Data Index: 2990733 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.7067. Min Act: -0.1700
Data Index: 3248062 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.6754. Min Act: -0.1700
Data Index: 32635 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.7067. Min Act: -0.1700
Data Index: 6463765 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.7067. Min Act: -0.1700
Data Index: 5535337 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.7067. Min Act: -0.1700
Data Index: 2515564 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.7067. Min Act: -0.1700
Data Index: 4766283 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.6754. Min Act: -0.1700
Data Index: 6718920 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.6754. Min Act: -0.1700
Data Index: 7052769 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.6754. Min Act: -0.1700
Data Index: 6075574 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19