Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1599 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.9562. Min Act: -0.1700
Data Index: 5691918 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.9246. Min Act: -0.1700
Data Index: 4589140 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.9246. Min Act: -0.1700
Data Index: 8819165 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.8134. Min Act: -0.1700
Data Index: 8786137 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.8611. Min Act: -0.1700
Data Index: 7323782 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.8611. Min Act: -0.1700
Data Index: 21347 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.8293. Min Act: -0.1700
Data Index: 2742877 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.8293. Min Act: -0.1700
Data Index: 7531358 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.8452. Min Act: -0.1700
Data Index: 4668494 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.8293. Min Act: -0.1700
Data Index: 5541014 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.8134. Min Act: -0.1700
Data Index: 429859 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.8134. Min Act: -0.1700
Data Index: 4376760 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.8134. Min Act: -0.1700
Data Index: 3195717 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.7816. Min Act: -0.1700
Data Index: 5271788 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.7975. Min Act: -0.1700
Data Index: 7554564 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.7975. Min Act: -0.1700
Data Index: 6646094 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.8134. Min Act: -0.1700
Data Index: 3509835 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.7656. Min Act: -0.1700
Data Index: 1862273 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.7816. Min Act: -0.1700
Data Index: 1823627 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9562. Min Range: -2.9562
Max Act: 2.7656. Min Act: -0.1700
Data Index: 2005924 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19