Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2201 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.9108. Min Act: -0.1700
Data Index: 3684806 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.8795. Min Act: -0.1700
Data Index: 7530669 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.7858. Min Act: -0.1700
Data Index: 157146 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.6608. Min Act: -0.1700
Data Index: 6797046 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.6608. Min Act: -0.1700
Data Index: 4636806 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.5670. Min Act: -0.1700
Data Index: 3050488 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4733. Min Act: -0.1700
Data Index: 6075773 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4733. Min Act: -0.1700
Data Index: 1087732 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4733. Min Act: -0.1700
Data Index: 7273636 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4733. Min Act: -0.1700
Data Index: 5515416 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4420. Min Act: -0.1700
Data Index: 352686 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4733. Min Act: -0.1700
Data Index: 467655 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4420. Min Act: -0.1700
Data Index: 4592787 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.3795. Min Act: -0.1700
Data Index: 8109657 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4108. Min Act: -0.1700
Data Index: 5149119 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4108. Min Act: -0.1700
Data Index: 1845441 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4420. Min Act: -0.1700
Data Index: 6653927 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4420. Min Act: -0.1700
Data Index: 4773427 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4420. Min Act: -0.1700
Data Index: 6595168 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.3795. Min Act: -0.1700
Data Index: 7373764 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19