Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3198 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.5690. Min Act: -0.1700
Data Index: 5562697 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.5533. Min Act: -0.1700
Data Index: 7636685 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.5533. Min Act: -0.1700
Data Index: 8286661 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.5533. Min Act: -0.1700
Data Index: 1194660 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.5376. Min Act: -0.1700
Data Index: 5679404 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.5220. Min Act: -0.1700
Data Index: 4490041 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.5063. Min Act: -0.1700
Data Index: 6942922 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.5063. Min Act: -0.1700
Data Index: 3058 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.4750. Min Act: -0.1700
Data Index: 516585 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.4750. Min Act: -0.1700
Data Index: 5250334 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.4593. Min Act: -0.1700
Data Index: 5923450 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.4593. Min Act: -0.1700
Data Index: 3375841 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.4437. Min Act: -0.1700
Data Index: 8558263 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.4280. Min Act: -0.1700
Data Index: 8178660 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.4123. Min Act: -0.1700
Data Index: 1947313 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.4280. Min Act: -0.1700
Data Index: 2243915 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.4280. Min Act: -0.1700
Data Index: 39605 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.4123. Min Act: -0.1700
Data Index: 155739 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.4123. Min Act: -0.1700
Data Index: 6025608 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5690. Min Range: -3.5690
Max Act: 3.3966. Min Act: -0.1700
Data Index: 4669401 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19