Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 614 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.6549. Min Act: -0.1700
Data Index: 2072850 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.5924. Min Act: -0.1700
Data Index: 5230433 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.5299. Min Act: -0.1700
Data Index: 338191 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4987. Min Act: -0.1700
Data Index: 3389847 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4987. Min Act: -0.1700
Data Index: 649101 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4987. Min Act: -0.1700
Data Index: 5205199 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4674. Min Act: -0.1700
Data Index: 2168802 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4674. Min Act: -0.1700
Data Index: 2082435 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4362. Min Act: -0.1700
Data Index: 7594258 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4049. Min Act: -0.1700
Data Index: 6141435 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4049. Min Act: -0.1700
Data Index: 1498852 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4049. Min Act: -0.1700
Data Index: 6754898 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4049. Min Act: -0.1700
Data Index: 8361866 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4049. Min Act: -0.1700
Data Index: 4347939 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.4049. Min Act: -0.1700
Data Index: 2584734 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.3424. Min Act: -0.1700
Data Index: 6803290 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.3424. Min Act: -0.1700
Data Index: 8674628 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.3424. Min Act: -0.1700
Data Index: 1240891 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.3112. Min Act: -0.1700
Data Index: 4547454 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6549. Min Range: -5.6549
Max Act: 5.3112. Min Act: -0.1700
Data Index: 8273570 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19