Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 931 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0680. Min Range: -6.0680
Max Act: 6.0680. Min Act: -0.1700
Data Index: 8302047 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0680. Min Range: -6.0680
Max Act: 6.0368. Min Act: -0.1700
Data Index: 5905252 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.9430. Min Act: -0.1700
Data Index: 1499963 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.9118. Min Act: -0.1700
Data Index: 202949 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.9118. Min Act: -0.1700
Data Index: 6745704 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.8805. Min Act: -0.1700
Data Index: 4720467 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.8493. Min Act: -0.1700
Data Index: 700458 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.8805. Min Act: -0.1700
Data Index: 7896684 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.8180. Min Act: -0.1700
Data Index: 3877167 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.7243. Min Act: -0.1700
Data Index: 4272958 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.7555. Min Act: -0.1700
Data Index: 7900714 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.6930. Min Act: -0.1700
Data Index: 1371511 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.6930. Min Act: -0.1700
Data Index: 6851480 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.7555. Min Act: -0.1700
Data Index: 4247458 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.6930. Min Act: -0.1700
Data Index: 3799776 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.6930. Min Act: -0.1700
Data Index: 8456 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.6930. Min Act: -0.1700
Data Index: 6166629 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.6930. Min Act: -0.1700
Data Index: 984847 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.6930. Min Act: -0.1700
Data Index: 7900716 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0680. Min Range: -6.0680
Max Act: 5.6618. Min Act: -0.1700
Data Index: 363110 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19