Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2232 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.2912. Min Act: -0.1700
Data Index: 1309825 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.2287. Min Act: -0.1700
Data Index: 4281115 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.2912. Min Act: -0.1700
Data Index: 5065621 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.1662. Min Act: -0.1700
Data Index: 1279467 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.0412. Min Act: -0.1700
Data Index: 5313897 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.1037. Min Act: -0.1700
Data Index: 881746 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.1037. Min Act: -0.1700
Data Index: 1218196 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.1350. Min Act: -0.1700
Data Index: 7401996 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.1037. Min Act: -0.1700
Data Index: 2351915 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.0099. Min Act: -0.1700
Data Index: 475084 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.0724. Min Act: -0.1700
Data Index: 8729157 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.1037. Min Act: -0.1700
Data Index: 2989720 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.1350. Min Act: -0.1700
Data Index: 4758767 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.0724. Min Act: -0.1700
Data Index: 2079737 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.0724. Min Act: -0.1700
Data Index: 8547518 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.0099. Min Act: -0.1700
Data Index: 6273567 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.0724. Min Act: -0.1700
Data Index: 2099084 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.1037. Min Act: -0.1700
Data Index: 6873754 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2912. Min Range: -4.2912
Max Act: 3.9787. Min Act: -0.1700
Data Index: 7857894 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2912. Min Range: -4.2912
Max Act: 4.0099. Min Act: -0.1700
Data Index: 5730710 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19