Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1255 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.7846. Min Act: -0.1700
Data Index: 3977802 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.6595. Min Act: -0.1700
Data Index: 427573 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.6282. Min Act: -0.1700
Data Index: 2004072 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.6282. Min Act: -0.1700
Data Index: 7633667 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.6125. Min Act: -0.1700
Data Index: 5948323 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.6125. Min Act: -0.1700
Data Index: 6629629 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.6125. Min Act: -0.1700
Data Index: 4008201 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.5969. Min Act: -0.1700
Data Index: 5510609 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.5812. Min Act: -0.1700
Data Index: 224307 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.5499. Min Act: -0.1700
Data Index: 2215111 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.5656. Min Act: -0.1700
Data Index: 8292689 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.5812. Min Act: -0.1700
Data Index: 8292690 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.5342. Min Act: -0.1700
Data Index: 2846260 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.5186. Min Act: -0.1700
Data Index: 6181412 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.5029. Min Act: -0.1700
Data Index: 8690861 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.5186. Min Act: -0.1700
Data Index: 1373513 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.4716. Min Act: -0.1700
Data Index: 6077265 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.4873. Min Act: -0.1700
Data Index: 890603 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.5029. Min Act: -0.1700
Data Index: 4225784 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7846. Min Range: -3.7846
Max Act: 3.4873. Min Act: -0.1700
Data Index: 1559878 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19