Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2091 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.3465. Min Act: -0.1700
Data Index: 6967932 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.2528. Min Act: -0.1700
Data Index: 6388628 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.1903. Min Act: -0.1700
Data Index: 3421410 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.2215. Min Act: -0.1700
Data Index: 717199 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.1903. Min Act: -0.1700
Data Index: 6377569 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.1590. Min Act: -0.1700
Data Index: 246971 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.1590. Min Act: -0.1700
Data Index: 8450675 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.1278. Min Act: -0.1700
Data Index: 306872 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.1278. Min Act: -0.1700
Data Index: 3086886 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.1590. Min Act: -0.1700
Data Index: 2303362 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.0965. Min Act: -0.1700
Data Index: 2952775 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.0965. Min Act: -0.1700
Data Index: 7754069 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.0652. Min Act: -0.1700
Data Index: 8286763 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.0965. Min Act: -0.1700
Data Index: 148441 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.0652. Min Act: -0.1700
Data Index: 921477 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.0652. Min Act: -0.1700
Data Index: 6538641 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.0652. Min Act: -0.1700
Data Index: 6249683 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.0652. Min Act: -0.1700
Data Index: 8785608 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.0652. Min Act: -0.1700
Data Index: 3725796 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3465. Min Range: -4.3465
Max Act: 4.0340. Min Act: -0.1700
Data Index: 6647679 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19