Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4933 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.0026. Min Range: -13.0026
Max Act: 13.0026. Min Act: -0.1700
Data Index: 3036562 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.5026. Min Act: -0.1700
Data Index: 3106361 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.4401. Min Act: -0.1700
Data Index: 6156171 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.4401. Min Act: -0.1700
Data Index: 143026 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.3776. Min Act: -0.1700
Data Index: 5181047 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.3776. Min Act: -0.1700
Data Index: 4738752 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.3776. Min Act: -0.1700
Data Index: 6285082 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.3151. Min Act: -0.1700
Data Index: 5093489 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.2526. Min Act: -0.1700
Data Index: 3356102 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.3151. Min Act: -0.1700
Data Index: 8472501 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.2526. Min Act: -0.1700
Data Index: 5604784 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.2526. Min Act: -0.1700
Data Index: 5193278 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.1901. Min Act: -0.1700
Data Index: 8027905 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.1901. Min Act: -0.1700
Data Index: 3906855 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.1901. Min Act: -0.1700
Data Index: 6793216 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.1901. Min Act: -0.1700
Data Index: 5794348 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.1901. Min Act: -0.1700
Data Index: 8233258 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.1901. Min Act: -0.1700
Data Index: 4583746 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.1901. Min Act: -0.1700
Data Index: 8339096 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0026. Min Range: -13.0026
Max Act: 12.1901. Min Act: -0.1700
Data Index: 4675978 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19