Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3779 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.3547. Min Act: -0.1700
Data Index: 7867358 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.3547. Min Act: -0.1700
Data Index: 6673565 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2922. Min Act: -0.1700
Data Index: 7342575 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.3234. Min Act: -0.1700
Data Index: 8088532 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2922. Min Act: -0.1700
Data Index: 4170331 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2922. Min Act: -0.1700
Data Index: 900054 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2609. Min Act: -0.1700
Data Index: 2785626 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1984. Min Act: -0.1700
Data Index: 2567156 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2297. Min Act: -0.1700
Data Index: 5869489 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1984. Min Act: -0.1700
Data Index: 5386276 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1984. Min Act: -0.1700
Data Index: 6942515 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1672. Min Act: -0.1700
Data Index: 2003627 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1672. Min Act: -0.1700
Data Index: 4322190 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1359. Min Act: -0.1700
Data Index: 8267255 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1047. Min Act: -0.1700
Data Index: 722159 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1047. Min Act: -0.1700
Data Index: 7548938 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.0734. Min Act: -0.1700
Data Index: 4517240 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.0734. Min Act: -0.1700
Data Index: 783941 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1047. Min Act: -0.1700
Data Index: 6276834 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.0734. Min Act: -0.1700
Data Index: 6792983 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19