Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2827 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1896. Min Range: -4.1896
Max Act: 4.1896. Min Act: -0.1700
Data Index: 6809271 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.9708. Min Act: -0.1700
Data Index: 8233813 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1896. Min Range: -4.1896
Max Act: 4.0021. Min Act: -0.1700
Data Index: 1279282 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.8457. Min Act: -0.1700
Data Index: 6382940 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.8457. Min Act: -0.1700
Data Index: 7769215 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.7832. Min Act: -0.1700
Data Index: 5147603 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.8145. Min Act: -0.1700
Data Index: 5658405 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.8145. Min Act: -0.1700
Data Index: 4019885 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.8145. Min Act: -0.1700
Data Index: 8731435 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.7519. Min Act: -0.1700
Data Index: 2673893 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.7519. Min Act: -0.1700
Data Index: 3273201 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.7519. Min Act: -0.1700
Data Index: 6483677 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.7519. Min Act: -0.1700
Data Index: 6072456 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.7206. Min Act: -0.1700
Data Index: 4526268 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.7206. Min Act: -0.1700
Data Index: 4698805 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.7206. Min Act: -0.1700
Data Index: 2408752 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.7206. Min Act: -0.1700
Data Index: 7405832 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.6893. Min Act: -0.1700
Data Index: 7773020 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.7206. Min Act: -0.1700
Data Index: 3477977 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1896. Min Range: -4.1896
Max Act: 3.7206. Min Act: -0.1700
Data Index: 1339466 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19