Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1461 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6155. Min Range: -9.6155
Max Act: 9.6155. Min Act: -0.1700
Data Index: 5880366 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6155. Min Range: -9.6155
Max Act: 9.5530. Min Act: -0.1700
Data Index: 8344230 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6155. Min Range: -9.6155
Max Act: 9.1780. Min Act: -0.1700
Data Index: 6785594 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6155. Min Range: -9.6155
Max Act: 9.0530. Min Act: -0.1700
Data Index: 5780696 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6155. Min Range: -9.6155
Max Act: 9.0530. Min Act: -0.1700
Data Index: 1909034 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.9905. Min Act: -0.1700
Data Index: 8434984 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.9280. Min Act: -0.1700
Data Index: 7089382 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.9280. Min Act: -0.1700
Data Index: 8470042 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.8655. Min Act: -0.1700
Data Index: 7942397 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.8655. Min Act: -0.1700
Data Index: 4082176 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.8655. Min Act: -0.1700
Data Index: 7325257 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.8655. Min Act: -0.1700
Data Index: 1002223 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.8655. Min Act: -0.1700
Data Index: 2180415 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.8030. Min Act: -0.1700
Data Index: 7619934 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.8030. Min Act: -0.1700
Data Index: 6250364 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.8030. Min Act: -0.1700
Data Index: 3767276 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.8030. Min Act: -0.1700
Data Index: 5998396 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.8030. Min Act: -0.1700
Data Index: 4815 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.7405. Min Act: -0.1700
Data Index: 2801526 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6155. Min Range: -9.6155
Max Act: 8.7405. Min Act: -0.1700
Data Index: 1138553 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19