Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1541 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.9237. Min Act: -0.1700
Data Index: 1851911 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.8924. Min Act: -0.1700
Data Index: 4977194 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.8299. Min Act: -0.1700
Data Index: 3037889 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.7987. Min Act: -0.1700
Data Index: 7207269 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.7674. Min Act: -0.1700
Data Index: 7141153 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.7362. Min Act: -0.1700
Data Index: 1699666 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.7362. Min Act: -0.1700
Data Index: 3566997 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.7362. Min Act: -0.1700
Data Index: 931118 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.7049. Min Act: -0.1700
Data Index: 6925690 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.7049. Min Act: -0.1700
Data Index: 212279 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.6424. Min Act: -0.1700
Data Index: 3190538 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.6424. Min Act: -0.1700
Data Index: 4192016 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.6112. Min Act: -0.1700
Data Index: 6105406 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.6424. Min Act: -0.1700
Data Index: 2439131 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.6112. Min Act: -0.1700
Data Index: 8418079 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.6112. Min Act: -0.1700
Data Index: 4193375 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.5799. Min Act: -0.1700
Data Index: 6433329 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.5799. Min Act: -0.1700
Data Index: 8496754 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.5799. Min Act: -0.1700
Data Index: 7402567 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9237. Min Range: -5.9237
Max Act: 5.5487. Min Act: -0.1700
Data Index: 1267391 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19