Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1514 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0329. Min Range: -6.0329
Max Act: 6.0329. Min Act: -0.1700
Data Index: 2419839 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.9391. Min Act: -0.1700
Data Index: 4472350 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.7516. Min Act: -0.1700
Data Index: 3456078 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.6579. Min Act: -0.1700
Data Index: 5928729 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.6266. Min Act: -0.1700
Data Index: 5910911 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.6266. Min Act: -0.1700
Data Index: 168331 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5954. Min Act: -0.1700
Data Index: 1850772 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5954. Min Act: -0.1700
Data Index: 3936545 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5641. Min Act: -0.1700
Data Index: 7208070 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5641. Min Act: -0.1700
Data Index: 7322074 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5329. Min Act: -0.1700
Data Index: 317037 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5329. Min Act: -0.1700
Data Index: 7580175 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5016. Min Act: -0.1700
Data Index: 7373103 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5016. Min Act: -0.1700
Data Index: 7384834 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.4079. Min Act: -0.1700
Data Index: 6548611 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.4079. Min Act: -0.1700
Data Index: 3450484 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.3766. Min Act: -0.1700
Data Index: 1609419 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.3454. Min Act: -0.1700
Data Index: 4907332 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.3141. Min Act: -0.1700
Data Index: 3549130 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.3454. Min Act: -0.1700
Data Index: 27794 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19