Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.8618. Min Act: -0.1700
Data Index: 3749746 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.8305. Min Act: -0.1700
Data Index: 5931005 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7993. Min Act: -0.1700
Data Index: 1518078 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7368. Min Act: -0.1700
Data Index: 4888188 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6743. Min Act: -0.1700
Data Index: 6016154 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6430. Min Act: -0.1700
Data Index: 6780582 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6430. Min Act: -0.1700
Data Index: 7455515 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.5493. Min Act: -0.1700
Data Index: 750443 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.5805. Min Act: -0.1700
Data Index: 5282058 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.5493. Min Act: -0.1700
Data Index: 6030663 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.5805. Min Act: -0.1700
Data Index: 429745 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.5493. Min Act: -0.1700
Data Index: 2718550 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.5493. Min Act: -0.1700
Data Index: 5922863 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.5180. Min Act: -0.1700
Data Index: 4296907 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.4868. Min Act: -0.1700
Data Index: 533356 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.4555. Min Act: -0.1700
Data Index: 8007222 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.4555. Min Act: -0.1700
Data Index: 7385992 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.4868. Min Act: -0.1700
Data Index: 4296909 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.4868. Min Act: -0.1700
Data Index: 6459028 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.4868. Min Act: -0.1700
Data Index: 4286296 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19