Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5206 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.8524. Min Act: -0.1700
Data Index: 6494227 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.8212. Min Act: -0.1700
Data Index: 5670577 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.8212. Min Act: -0.1700
Data Index: 3305584 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.8212. Min Act: -0.1700
Data Index: 3950616 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.7587. Min Act: -0.1700
Data Index: 7562016 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.7587. Min Act: -0.1700
Data Index: 7756307 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.7274. Min Act: -0.1700
Data Index: 657260 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.6962. Min Act: -0.1700
Data Index: 78904 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.6962. Min Act: -0.1700
Data Index: 1468922 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.6962. Min Act: -0.1700
Data Index: 3806304 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.7274. Min Act: -0.1700
Data Index: 8812406 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.6962. Min Act: -0.1700
Data Index: 949554 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.6962. Min Act: -0.1700
Data Index: 7310629 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.6962. Min Act: -0.1700
Data Index: 5466508 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.6649. Min Act: -0.1700
Data Index: 8479923 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.6649. Min Act: -0.1700
Data Index: 2409882 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.6337. Min Act: -0.1700
Data Index: 234557 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.6337. Min Act: -0.1700
Data Index: 6774032 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.6337. Min Act: -0.1700
Data Index: 7061406 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8524. Min Range: -5.8524
Max Act: 5.6337. Min Act: -0.1700
Data Index: 7410883 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19