Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1598 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.4050. Min Act: -0.1700
Data Index: 4865719 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.2175. Min Act: -0.1700
Data Index: 1726045 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.1238. Min Act: -0.1700
Data Index: 5178297 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.1550. Min Act: -0.1700
Data Index: 1811614 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.0613. Min Act: -0.1700
Data Index: 2646445 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.9988. Min Act: -0.1700
Data Index: 8125514 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.9988. Min Act: -0.1700
Data Index: 3775128 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.9988. Min Act: -0.1700
Data Index: 4560582 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.0300. Min Act: -0.1700
Data Index: 4882011 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.9363. Min Act: -0.1700
Data Index: 1616528 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.9675. Min Act: -0.1700
Data Index: 5565063 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.9675. Min Act: -0.1700
Data Index: 1216606 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.9675. Min Act: -0.1700
Data Index: 1000895 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.9675. Min Act: -0.1700
Data Index: 7791351 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.9363. Min Act: -0.1700
Data Index: 1854418 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.9363. Min Act: -0.1700
Data Index: 8594566 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.9363. Min Act: -0.1700
Data Index: 4500431 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.9050. Min Act: -0.1700
Data Index: 6614196 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.9050. Min Act: -0.1700
Data Index: 3572033 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.8738. Min Act: -0.1700
Data Index: 6823049 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19