Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6149 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4725. Min Range: -6.4725
Max Act: 6.4725. Min Act: -0.1700
Data Index: 1906963 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4725. Min Range: -6.4725
Max Act: 6.1288. Min Act: -0.1700
Data Index: 7327294 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4725. Min Range: -6.4725
Max Act: 6.0350. Min Act: -0.1700
Data Index: 876065 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4725. Min Range: -6.4725
Max Act: 6.0038. Min Act: -0.1700
Data Index: 1333580 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.9413. Min Act: -0.1700
Data Index: 8052989 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.9100. Min Act: -0.1700
Data Index: 2818621 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.8475. Min Act: -0.1700
Data Index: 7771333 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.8163. Min Act: -0.1700
Data Index: 4063233 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.8163. Min Act: -0.1700
Data Index: 6768845 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.7850. Min Act: -0.1700
Data Index: 1332427 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.8163. Min Act: -0.1700
Data Index: 3391253 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.7850. Min Act: -0.1700
Data Index: 6998130 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.7538. Min Act: -0.1700
Data Index: 3304701 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.7538. Min Act: -0.1700
Data Index: 2183474 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.7538. Min Act: -0.1700
Data Index: 5848875 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.7538. Min Act: -0.1700
Data Index: 1013286 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.7538. Min Act: -0.1700
Data Index: 1006259 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.7538. Min Act: -0.1700
Data Index: 7782609 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.6913. Min Act: -0.1700
Data Index: 1295081 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4725. Min Range: -6.4725
Max Act: 5.6913. Min Act: -0.1700
Data Index: 5513566 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19