Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 920 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.6097. Min Act: -0.1700
Data Index: 7567190 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.5472. Min Act: -0.1700
Data Index: 5191183 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.4847. Min Act: -0.1700
Data Index: 4210337 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.2972. Min Act: -0.1700
Data Index: 4587837 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.2660. Min Act: -0.1700
Data Index: 5147117 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.2035. Min Act: -0.1700
Data Index: 5044729 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.1409. Min Act: -0.1700
Data Index: 2748699 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.1722. Min Act: -0.1700
Data Index: 3291247 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.1097. Min Act: -0.1700
Data Index: 1100252 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.1097. Min Act: -0.1700
Data Index: 627667 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.0784. Min Act: -0.1700
Data Index: 4946837 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.0784. Min Act: -0.1700
Data Index: 796528 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.1097. Min Act: -0.1700
Data Index: 2368292 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.0472. Min Act: -0.1700
Data Index: 1152508 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.0159. Min Act: -0.1700
Data Index: 5352762 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.0784. Min Act: -0.1700
Data Index: 4012885 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.0472. Min Act: -0.1700
Data Index: 4497321 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.0159. Min Act: -0.1700
Data Index: 2305699 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.0159. Min Act: -0.1700
Data Index: 3278833 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6097. Min Range: -4.6097
Max Act: 4.0159. Min Act: -0.1700
Data Index: 3719806 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19