Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4477 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1189. Min Range: -4.1189
Max Act: 4.1189. Min Act: -0.1700
Data Index: 3399413 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1189. Min Range: -4.1189
Max Act: 4.1189. Min Act: -0.1700
Data Index: 3510071 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1189. Min Range: -4.1189
Max Act: 4.1189. Min Act: -0.1700
Data Index: 262004 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.9939. Min Act: -0.1700
Data Index: 8727144 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.9314. Min Act: -0.1700
Data Index: 8217706 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.9314. Min Act: -0.1700
Data Index: 6330623 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.9314. Min Act: -0.1700
Data Index: 2951928 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.9314. Min Act: -0.1700
Data Index: 7808480 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.9001. Min Act: -0.1700
Data Index: 7083457 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.9001. Min Act: -0.1700
Data Index: 4827856 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.8688. Min Act: -0.1700
Data Index: 4392868 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.9001. Min Act: -0.1700
Data Index: 4088478 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.8688. Min Act: -0.1700
Data Index: 5525784 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.8376. Min Act: -0.1700
Data Index: 7150274 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.8376. Min Act: -0.1700
Data Index: 2452900 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.8063. Min Act: -0.1700
Data Index: 2184054 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.7750. Min Act: -0.1700
Data Index: 8662960 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.8063. Min Act: -0.1700
Data Index: 263367 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.8063. Min Act: -0.1700
Data Index: 4725174 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1189. Min Range: -4.1189
Max Act: 3.7750. Min Act: -0.1700
Data Index: 3537262 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19