Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2067 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 20.4655. Min Range: -20.4655
Max Act: 20.4655. Min Act: -0.1700
Data Index: 121337 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.7155. Min Act: -0.1700
Data Index: 7822968 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.7155. Min Act: -0.1700
Data Index: 1184731 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.7155. Min Act: -0.1700
Data Index: 694800 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.5905. Min Act: -0.1700
Data Index: 764701 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.5905. Min Act: -0.1700
Data Index: 7784736 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.5905. Min Act: -0.1700
Data Index: 1184732 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.4655. Min Act: -0.1700
Data Index: 764744 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.4655. Min Act: -0.1700
Data Index: 3805590 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.5905. Min Act: -0.1700
Data Index: 7784737 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.4655. Min Act: -0.1700
Data Index: 770165 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.4655. Min Act: -0.1700
Data Index: 7784735 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.4655. Min Act: -0.1700
Data Index: 764700 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.2155. Min Act: -0.1700
Data Index: 2235873 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.3405. Min Act: -0.1700
Data Index: 7450565 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.3405. Min Act: -0.1700
Data Index: 4192849 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.3405. Min Act: -0.1700
Data Index: 3372823 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.3405. Min Act: -0.1700
Data Index: 694795 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.2155. Min Act: -0.1700
Data Index: 675188 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 20.4655. Min Range: -20.4655
Max Act: 19.2155. Min Act: -0.1700
Data Index: 7110162 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19