Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 605 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0812. Min Range: -5.0812
Max Act: 5.0812. Min Act: -0.1700
Data Index: 7846337 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.8937. Min Act: -0.1700
Data Index: 2788367 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.7687. Min Act: -0.1700
Data Index: 1352976 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.7687. Min Act: -0.1700
Data Index: 8379188 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.7374. Min Act: -0.1700
Data Index: 3267733 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.7374. Min Act: -0.1700
Data Index: 3726430 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.7687. Min Act: -0.1700
Data Index: 6356257 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.7374. Min Act: -0.1700
Data Index: 5323679 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.7062. Min Act: -0.1700
Data Index: 5418144 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.7062. Min Act: -0.1700
Data Index: 8126757 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.7374. Min Act: -0.1700
Data Index: 1654763 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.7062. Min Act: -0.1700
Data Index: 8021584 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.7062. Min Act: -0.1700
Data Index: 3876932 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.6437. Min Act: -0.1700
Data Index: 8133317 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.6749. Min Act: -0.1700
Data Index: 5461277 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.6437. Min Act: -0.1700
Data Index: 5872299 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.6437. Min Act: -0.1700
Data Index: 2983547 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.7062. Min Act: -0.1700
Data Index: 2928203 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.6124. Min Act: -0.1700
Data Index: 2963769 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0812. Min Range: -5.0812
Max Act: 4.6437. Min Act: -0.1700
Data Index: 2043429 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19