Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1323 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.8703. Min Act: -0.1700
Data Index: 2031806 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.8861. Min Act: -0.1700
Data Index: 8661787 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.8703. Min Act: -0.1700
Data Index: 3461278 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.8067. Min Act: -0.1700
Data Index: 142168 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.8067. Min Act: -0.1700
Data Index: 7616700 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.7907. Min Act: -0.1700
Data Index: 6134170 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.7748. Min Act: -0.1700
Data Index: 3149705 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.7748. Min Act: -0.1700
Data Index: 3907176 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.7748. Min Act: -0.1700
Data Index: 3006597 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.7589. Min Act: -0.1700
Data Index: 6691404 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.7269. Min Act: -0.1700
Data Index: 7117040 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.7269. Min Act: -0.1700
Data Index: 2995366 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.7269. Min Act: -0.1700
Data Index: 7477405 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.7589. Min Act: -0.1700
Data Index: 1216185 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.6949. Min Act: -0.1700
Data Index: 7439267 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.6949. Min Act: -0.1700
Data Index: 1843139 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.6949. Min Act: -0.1700
Data Index: 7144727 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.6789. Min Act: -0.1700
Data Index: 89124 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.6949. Min Act: -0.1700
Data Index: 3082699 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8861. Min Range: -2.8861
Max Act: 2.7109. Min Act: -0.1700
Data Index: 219366 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19