Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2750 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.5589. Min Act: -0.1700
Data Index: 6950032 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.3714. Min Act: -0.1700
Data Index: 5897956 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.3089. Min Act: -0.1700
Data Index: 7552210 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.3089. Min Act: -0.1700
Data Index: 1060508 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.2777. Min Act: -0.1700
Data Index: 6739589 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.2464. Min Act: -0.1700
Data Index: 8165995 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.2152. Min Act: -0.1700
Data Index: 5809333 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.1839. Min Act: -0.1700
Data Index: 7015550 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.1839. Min Act: -0.1700
Data Index: 1581690 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.1527. Min Act: -0.1700
Data Index: 4080645 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.1527. Min Act: -0.1700
Data Index: 4466710 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.1527. Min Act: -0.1700
Data Index: 885069 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.1214. Min Act: -0.1700
Data Index: 7723836 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.0902. Min Act: -0.1700
Data Index: 2216834 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.1214. Min Act: -0.1700
Data Index: 5170963 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.0902. Min Act: -0.1700
Data Index: 2840942 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.0902. Min Act: -0.1700
Data Index: 4729694 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.0902. Min Act: -0.1700
Data Index: 6293536 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.0902. Min Act: -0.1700
Data Index: 5450588 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5589. Min Range: -5.5589
Max Act: 5.0589. Min Act: -0.1700
Data Index: 3406961 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19