Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5041 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.6776. Min Act: -0.1700
Data Index: 1827183 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.5839. Min Act: -0.1700
Data Index: 576371 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.3964. Min Act: -0.1700
Data Index: 6456946 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.3964. Min Act: -0.1700
Data Index: 811561 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.3651. Min Act: -0.1700
Data Index: 1519952 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.2714. Min Act: -0.1700
Data Index: 6612501 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.3026. Min Act: -0.1700
Data Index: 277429 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.3026. Min Act: -0.1700
Data Index: 1089941 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.2714. Min Act: -0.1700
Data Index: 6434891 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.2401. Min Act: -0.1700
Data Index: 4250798 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.2714. Min Act: -0.1700
Data Index: 2277491 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.2714. Min Act: -0.1700
Data Index: 8719352 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.2401. Min Act: -0.1700
Data Index: 3577516 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.2089. Min Act: -0.1700
Data Index: 5641045 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.2089. Min Act: -0.1700
Data Index: 8726423 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.2089. Min Act: -0.1700
Data Index: 6529707 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.1776. Min Act: -0.1700
Data Index: 6661753 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.1776. Min Act: -0.1700
Data Index: 69450 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.1776. Min Act: -0.1700
Data Index: 7961552 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6776. Min Range: -6.6776
Max Act: 6.1464. Min Act: -0.1700
Data Index: 3353573 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19