Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3361 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7842. Min Range: -5.7842
Max Act: 5.7842. Min Act: -0.1700
Data Index: 1770102 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7842. Min Range: -5.7842
Max Act: 5.7530. Min Act: -0.1700
Data Index: 1770097 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7842. Min Range: -5.7842
Max Act: 5.3780. Min Act: -0.1700
Data Index: 1770100 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7842. Min Range: -5.7842
Max Act: 5.1592. Min Act: -0.1700
Data Index: 5805446 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7842. Min Range: -5.7842
Max Act: 5.0655. Min Act: -0.1700
Data Index: 5271350 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7842. Min Range: -5.7842
Max Act: 5.0655. Min Act: -0.1700
Data Index: 8005904 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7842. Min Range: -5.7842
Max Act: 5.0342. Min Act: -0.1700
Data Index: 2633665 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7842. Min Range: -5.7842
Max Act: 5.0655. Min Act: -0.1700
Data Index: 1442322 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7842. Min Range: -5.7842
Max Act: 5.0030. Min Act: -0.1700
Data Index: 4129112 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7842. Min Range: -5.7842
Max Act: 5.0030. Min Act: -0.1700
Data Index: 5555845 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7842. Min Range: -5.7842
Max Act: 5.0030. Min Act: -0.1700
Data Index: 3713379 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7842. Min Range: -5.7842
Max Act: 4.9717. Min Act: -0.1700
Data Index: 1798827 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7842. Min Range: -5.7842
Max Act: 4.9717. Min Act: -0.1700
Data Index: 4048761 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7842. Min Range: -5.7842
Max Act: 4.9405. Min Act: -0.1700
Data Index: 5555843 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7842. Min Range: -5.7842
Max Act: 4.9405. Min Act: -0.1700
Data Index: 528643 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7842. Min Range: -5.7842
Max Act: 4.9092. Min Act: -0.1700
Data Index: 5555842 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7842. Min Range: -5.7842
Max Act: 4.9092. Min Act: -0.1700
Data Index: 5555839 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7842. Min Range: -5.7842
Max Act: 4.9405. Min Act: -0.1700
Data Index: 2372204 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7842. Min Range: -5.7842
Max Act: 4.9405. Min Act: -0.1700
Data Index: 2016658 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7842. Min Range: -5.7842
Max Act: 4.9092. Min Act: -0.1700
Data Index: 3293105 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19