Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2989 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1781. Min Range: -7.1781
Max Act: 7.1781. Min Act: -0.1700
Data Index: 1896350 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1781. Min Range: -7.1781
Max Act: 7.0218. Min Act: -0.1700
Data Index: 1915158 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.9906. Min Act: -0.1700
Data Index: 1741388 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.8343. Min Act: -0.1700
Data Index: 6772258 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.7718. Min Act: -0.1700
Data Index: 3765115 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.8031. Min Act: -0.1700
Data Index: 1810910 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.6781. Min Act: -0.1700
Data Index: 5771598 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.6781. Min Act: -0.1700
Data Index: 8006380 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.6781. Min Act: -0.1700
Data Index: 382677 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.6468. Min Act: -0.1700
Data Index: 1658572 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.6156. Min Act: -0.1700
Data Index: 3050031 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.6156. Min Act: -0.1700
Data Index: 4192742 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.5843. Min Act: -0.1700
Data Index: 160130 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.5531. Min Act: -0.1700
Data Index: 5024101 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.5218. Min Act: -0.1700
Data Index: 5651948 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.4906. Min Act: -0.1700
Data Index: 297329 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.4906. Min Act: -0.1700
Data Index: 1461620 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.4281. Min Act: -0.1700
Data Index: 4480777 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.4281. Min Act: -0.1700
Data Index: 3972431 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1781. Min Range: -7.1781
Max Act: 6.4281. Min Act: -0.1700
Data Index: 5254465 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19