Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3837 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.7901. Min Act: -0.1700
Data Index: 712512 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.7589. Min Act: -0.1700
Data Index: 3924171 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.7901. Min Act: -0.1700
Data Index: 1372958 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.7589. Min Act: -0.1700
Data Index: 8114295 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.7589. Min Act: -0.1700
Data Index: 6524155 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.7276. Min Act: -0.1700
Data Index: 1597141 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.7589. Min Act: -0.1700
Data Index: 7563841 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.6651. Min Act: -0.1700
Data Index: 1987566 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.6339. Min Act: -0.1700
Data Index: 564738 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.6339. Min Act: -0.1700
Data Index: 6729180 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.6339. Min Act: -0.1700
Data Index: 5840712 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.6026. Min Act: -0.1700
Data Index: 6661852 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.6026. Min Act: -0.1700
Data Index: 5920905 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.6026. Min Act: -0.1700
Data Index: 7114657 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.5714. Min Act: -0.1700
Data Index: 4110265 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.5714. Min Act: -0.1700
Data Index: 6208477 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.5714. Min Act: -0.1700
Data Index: 5072722 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.5714. Min Act: -0.1700
Data Index: 3128639 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.5401. Min Act: -0.1700
Data Index: 6007720 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7901. Min Range: -6.7901
Max Act: 6.5714. Min Act: -0.1700
Data Index: 2260710 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19