Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3661 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4660. Min Range: -8.4660
Max Act: 8.4035. Min Act: -0.1700
Data Index: 6295341 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4660. Min Range: -8.4660
Max Act: 8.4660. Min Act: -0.1700
Data Index: 7052672 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4660. Min Range: -8.4660
Max Act: 8.2160. Min Act: -0.1700
Data Index: 3362920 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4660. Min Range: -8.4660
Max Act: 8.2472. Min Act: -0.1700
Data Index: 7135788 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4660. Min Range: -8.4660
Max Act: 8.1535. Min Act: -0.1700
Data Index: 1378572 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4660. Min Range: -8.4660
Max Act: 8.0910. Min Act: -0.1700
Data Index: 7135784 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4660. Min Range: -8.4660
Max Act: 8.1222. Min Act: -0.1700
Data Index: 3434312 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4660. Min Range: -8.4660
Max Act: 8.0597. Min Act: -0.1700
Data Index: 2916881 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4660. Min Range: -8.4660
Max Act: 7.9972. Min Act: -0.1700
Data Index: 6586633 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4660. Min Range: -8.4660
Max Act: 7.9660. Min Act: -0.1700
Data Index: 6548300 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4660. Min Range: -8.4660
Max Act: 7.9035. Min Act: -0.1700
Data Index: 3889684 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4660. Min Range: -8.4660
Max Act: 7.9035. Min Act: -0.1700
Data Index: 7135789 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4660. Min Range: -8.4660
Max Act: 7.9347. Min Act: -0.1700
Data Index: 2277666 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4660. Min Range: -8.4660
Max Act: 7.9347. Min Act: -0.1700
Data Index: 4843629 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4660. Min Range: -8.4660
Max Act: 7.9035. Min Act: -0.1700
Data Index: 519900 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4660. Min Range: -8.4660
Max Act: 7.8722. Min Act: -0.1700
Data Index: 1684055 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4660. Min Range: -8.4660
Max Act: 7.8410. Min Act: -0.1700
Data Index: 5461266 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4660. Min Range: -8.4660
Max Act: 7.7785. Min Act: -0.1700
Data Index: 1684056 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4660. Min Range: -8.4660
Max Act: 7.7160. Min Act: -0.1700
Data Index: 3919184 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4660. Min Range: -8.4660
Max Act: 7.6847. Min Act: -0.1700
Data Index: 3396365 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19