Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2107 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.8964. Min Act: -0.1696
Data Index: 3785036 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.7852. Min Act: -0.1699
Data Index: 1416936 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.7373. Min Act: -0.1700
Data Index: 7053006 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.7373. Min Act: -0.1700
Data Index: 7415839 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.7053. Min Act: -0.1700
Data Index: 6504070 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.6573. Min Act: -0.1691
Data Index: 7168356 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.6252. Min Act: -0.1700
Data Index: 5211452 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.6573. Min Act: -0.1699
Data Index: 3785038 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.6412. Min Act: -0.1700
Data Index: 3785037 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.6252. Min Act: -0.1700
Data Index: 2606291 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.6252. Min Act: -0.1700
Data Index: 1581016 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.6252. Min Act: -0.1700
Data Index: 530602 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.6091. Min Act: -0.1700
Data Index: 8042269 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.5930. Min Act: -0.1700
Data Index: 1997736 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.5930. Min Act: -0.1695
Data Index: 5425730 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.5930. Min Act: -0.1700
Data Index: 107967 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.5930. Min Act: -0.1700
Data Index: 3221174 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.5769. Min Act: -0.1700
Data Index: 6244175 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.5769. Min Act: -0.1700
Data Index: 3512802 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8964. Min Range: -2.8964
Max Act: 2.5608. Min Act: -0.1700
Data Index: 2987613 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19