Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.8441. Min Act: -0.1700
Data Index: 3407199 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.8269. Min Act: -0.1700
Data Index: 1954260 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7926. Min Act: -0.1700
Data Index: 2933886 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7926. Min Act: -0.1700
Data Index: 2842295 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7926. Min Act: -0.1700
Data Index: 4512270 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7581. Min Act: -0.1700
Data Index: 2829626 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7753. Min Act: -0.1700
Data Index: 7892142 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7581. Min Act: -0.1700
Data Index: 4794478 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7581. Min Act: -0.1700
Data Index: 4569716 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7408. Min Act: -0.1700
Data Index: 8125 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7235. Min Act: -0.1700
Data Index: 2986651 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7062. Min Act: -0.1700
Data Index: 1404752 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7408. Min Act: -0.1700
Data Index: 5033126 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7062. Min Act: -0.1700
Data Index: 6698759 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7408. Min Act: -0.1700
Data Index: 3783595 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7408. Min Act: -0.1700
Data Index: 6672968 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7062. Min Act: -0.1700
Data Index: 5674266 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7062. Min Act: -0.1700
Data Index: 593372 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.7235. Min Act: -0.1700
Data Index: 785262 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8441. Min Range: -1.8441
Max Act: 1.6888. Min Act: -0.1700
Data Index: 836325 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19