Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1780 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.7285. Min Act: -0.1700
Data Index: 3101587 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.7597. Min Act: -0.1700
Data Index: 1934139 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.6972. Min Act: -0.1700
Data Index: 7803454 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.6035. Min Act: -0.1700
Data Index: 8332772 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.5722. Min Act: -0.1700
Data Index: 3954557 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.5097. Min Act: -0.1700
Data Index: 6965272 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.4472. Min Act: -0.1700
Data Index: 3502865 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.4472. Min Act: -0.1700
Data Index: 5871782 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.4472. Min Act: -0.1700
Data Index: 819 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.3535. Min Act: -0.1700
Data Index: 7584155 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.4472. Min Act: -0.1700
Data Index: 5661149 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.3847. Min Act: -0.1700
Data Index: 7507138 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.3222. Min Act: -0.1700
Data Index: 5949691 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.2597. Min Act: -0.1700
Data Index: 2912017 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.3222. Min Act: -0.1700
Data Index: 5391372 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.2597. Min Act: -0.1700
Data Index: 2725989 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.2597. Min Act: -0.1700
Data Index: 8212689 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.2597. Min Act: -0.1700
Data Index: 3807308 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.2910. Min Act: -0.1700
Data Index: 8559721 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.2597. Min Act: -0.1700
Data Index: 8581638 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19