Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2898. Min Range: -5.2898
Max Act: 5.2898. Min Act: -0.1700
Data Index: 6394237 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2898. Min Range: -5.2898
Max Act: 5.2585. Min Act: -0.1700
Data Index: 7953584 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2898. Min Range: -5.2898
Max Act: 5.0398. Min Act: -0.1700
Data Index: 1707501 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2898. Min Range: -5.2898
Max Act: 5.0085. Min Act: -0.1700
Data Index: 3799771 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.9773. Min Act: -0.1700
Data Index: 6204916 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2898. Min Range: -5.2898
Max Act: 5.0085. Min Act: -0.1700
Data Index: 7379764 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.9148. Min Act: -0.1700
Data Index: 8517256 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.9773. Min Act: -0.1700
Data Index: 3874187 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.9460. Min Act: -0.1700
Data Index: 3876843 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.9460. Min Act: -0.1700
Data Index: 3225567 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.9148. Min Act: -0.1700
Data Index: 8785387 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.9148. Min Act: -0.1700
Data Index: 2915203 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.9148. Min Act: -0.1700
Data Index: 7636241 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.9148. Min Act: -0.1700
Data Index: 559999 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.9148. Min Act: -0.1700
Data Index: 4061313 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.9148. Min Act: -0.1700
Data Index: 3926541 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.9148. Min Act: -0.1700
Data Index: 7106319 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.8835. Min Act: -0.1700
Data Index: 4373338 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.8835. Min Act: -0.1700
Data Index: 5961876 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2898. Min Range: -5.2898
Max Act: 4.9148. Min Act: -0.1700
Data Index: 5394345 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19