Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3588 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1021. Min Range: -5.1021
Max Act: 5.1021. Min Act: -0.1700
Data Index: 622111 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1021. Min Range: -5.1021
Max Act: 5.0709. Min Act: -0.1700
Data Index: 5824452 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1021. Min Range: -5.1021
Max Act: 5.0396. Min Act: -0.1700
Data Index: 3673406 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1021. Min Range: -5.1021
Max Act: 5.0084. Min Act: -0.1700
Data Index: 5525252 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1021. Min Range: -5.1021
Max Act: 5.0084. Min Act: -0.1700
Data Index: 7340407 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1021. Min Range: -5.1021
Max Act: 4.9771. Min Act: -0.1700
Data Index: 8334104 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1021. Min Range: -5.1021
Max Act: 5.0084. Min Act: -0.1700
Data Index: 7126505 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1021. Min Range: -5.1021
Max Act: 4.9771. Min Act: -0.1700
Data Index: 3863033 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1021. Min Range: -5.1021
Max Act: 4.9459. Min Act: -0.1700
Data Index: 2215684 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1021. Min Range: -5.1021
Max Act: 4.9146. Min Act: -0.1700
Data Index: 755197 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1021. Min Range: -5.1021
Max Act: 4.9459. Min Act: -0.1700
Data Index: 973738 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1021. Min Range: -5.1021
Max Act: 4.9459. Min Act: -0.1700
Data Index: 2945993 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1021. Min Range: -5.1021
Max Act: 4.9146. Min Act: -0.1700
Data Index: 658069 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1021. Min Range: -5.1021
Max Act: 4.9459. Min Act: -0.1700
Data Index: 3692463 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1021. Min Range: -5.1021
Max Act: 4.9146. Min Act: -0.1700
Data Index: 6161362 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1021. Min Range: -5.1021
Max Act: 4.9146. Min Act: -0.1700
Data Index: 8291643 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1021. Min Range: -5.1021
Max Act: 4.8521. Min Act: -0.1700
Data Index: 5718792 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1021. Min Range: -5.1021
Max Act: 4.8521. Min Act: -0.1700
Data Index: 1227065 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1021. Min Range: -5.1021
Max Act: 4.8209. Min Act: -0.1700
Data Index: 8099735 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1021. Min Range: -5.1021
Max Act: 4.8834. Min Act: -0.1700
Data Index: 2527747 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19