Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3226 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.7143. Min Act: -0.1700
Data Index: 1534001 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.6830. Min Act: -0.1700
Data Index: 7120852 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.5268. Min Act: -0.1700
Data Index: 8064460 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.5580. Min Act: -0.1700
Data Index: 6808155 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.4643. Min Act: -0.1700
Data Index: 3873312 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.4955. Min Act: -0.1700
Data Index: 5466627 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.4018. Min Act: -0.1700
Data Index: 5851304 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.3080. Min Act: -0.1700
Data Index: 1515397 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.2768. Min Act: -0.1700
Data Index: 7294905 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.2455. Min Act: -0.1700
Data Index: 5945447 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.2143. Min Act: -0.1700
Data Index: 6206030 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.1830. Min Act: -0.1700
Data Index: 4311041 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.2143. Min Act: -0.1700
Data Index: 382805 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.1518. Min Act: -0.1700
Data Index: 3915606 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.1518. Min Act: -0.1700
Data Index: 4109362 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.0893. Min Act: -0.1700
Data Index: 4859821 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.0893. Min Act: -0.1700
Data Index: 2232474 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.0893. Min Act: -0.1700
Data Index: 2290148 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.0580. Min Act: -0.1700
Data Index: 5335034 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7143. Min Range: -6.7143
Max Act: 6.0580. Min Act: -0.1700
Data Index: 4875113 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19