Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4885 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3861. Min Range: -3.3861
Max Act: 3.3861. Min Act: -0.1700
Data Index: 4554964 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3861. Min Range: -3.3861
Max Act: 3.2606. Min Act: -0.1700
Data Index: 3417969 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3861. Min Range: -3.3861
Max Act: 3.2134. Min Act: -0.1700
Data Index: 5157145 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3861. Min Range: -3.3861
Max Act: 3.1820. Min Act: -0.1700
Data Index: 1002086 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3861. Min Range: -3.3861
Max Act: 3.1190. Min Act: -0.1700
Data Index: 3418498 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3861. Min Range: -3.3861
Max Act: 3.0717. Min Act: -0.1700
Data Index: 6897442 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3861. Min Range: -3.3861
Max Act: 3.0244. Min Act: -0.1700
Data Index: 8596435 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3861. Min Range: -3.3861
Max Act: 3.0402. Min Act: -0.1700
Data Index: 1239559 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3861. Min Range: -3.3861
Max Act: 3.0086. Min Act: -0.1700
Data Index: 6004824 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3861. Min Range: -3.3861
Max Act: 2.9928. Min Act: -0.1700
Data Index: 2200286 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3861. Min Range: -3.3861
Max Act: 2.9770. Min Act: -0.1700
Data Index: 5149375 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3861. Min Range: -3.3861
Max Act: 2.9612. Min Act: -0.1700
Data Index: 773853 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3861. Min Range: -3.3861
Max Act: 2.9770. Min Act: -0.1700
Data Index: 5027489 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3861. Min Range: -3.3861
Max Act: 2.9612. Min Act: -0.1700
Data Index: 3489616 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3861. Min Range: -3.3861
Max Act: 2.9453. Min Act: -0.1700
Data Index: 3178586 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3861. Min Range: -3.3861
Max Act: 2.9453. Min Act: -0.1700
Data Index: 4801769 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3861. Min Range: -3.3861
Max Act: 2.9295. Min Act: -0.1700
Data Index: 4050408 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3861. Min Range: -3.3861
Max Act: 2.9453. Min Act: -0.1700
Data Index: 5202669 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3861. Min Range: -3.3861
Max Act: 2.9295. Min Act: -0.1700
Data Index: 8570837 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3861. Min Range: -3.3861
Max Act: 2.9295. Min Act: -0.1700
Data Index: 6098780 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19