Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2388 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.9725. Min Act: -0.1700
Data Index: 6120887 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8787. Min Act: -0.1700
Data Index: 858957 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8475. Min Act: -0.1700
Data Index: 768142 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8787. Min Act: -0.1700
Data Index: 8470407 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8787. Min Act: -0.1700
Data Index: 7180702 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8787. Min Act: -0.1700
Data Index: 2688295 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8475. Min Act: -0.1700
Data Index: 1189755 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8162. Min Act: -0.1700
Data Index: 2079736 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8162. Min Act: -0.1700
Data Index: 1047375 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8162. Min Act: -0.1700
Data Index: 844185 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8162. Min Act: -0.1700
Data Index: 234552 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8162. Min Act: -0.1700
Data Index: 7265467 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7850. Min Act: -0.1700
Data Index: 212730 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7850. Min Act: -0.1700
Data Index: 2773821 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7850. Min Act: -0.1700
Data Index: 3686281 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7850. Min Act: -0.1700
Data Index: 496000 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7850. Min Act: -0.1700
Data Index: 7978003 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7850. Min Act: -0.1700
Data Index: 768148 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7850. Min Act: -0.1700
Data Index: 2824384 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7225. Min Act: -0.1700
Data Index: 5365859 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19