Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3191. Min Range: -4.3191
Max Act: 4.3191. Min Act: -0.1700
Data Index: 1589354 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3191. Min Range: -4.3191
Max Act: 4.2253. Min Act: -0.1700
Data Index: 8175006 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3191. Min Range: -4.3191
Max Act: 4.1316. Min Act: -0.1700
Data Index: 1186879 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3191. Min Range: -4.3191
Max Act: 4.1316. Min Act: -0.1700
Data Index: 6660712 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3191. Min Range: -4.3191
Max Act: 4.1003. Min Act: -0.1700
Data Index: 2689012 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3191. Min Range: -4.3191
Max Act: 4.0691. Min Act: -0.1700
Data Index: 4006980 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3191. Min Range: -4.3191
Max Act: 4.0378. Min Act: -0.1700
Data Index: 4698385 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3191. Min Range: -4.3191
Max Act: 4.0378. Min Act: -0.1700
Data Index: 1562184 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3191. Min Range: -4.3191
Max Act: 4.0378. Min Act: -0.1700
Data Index: 3716556 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3191. Min Range: -4.3191
Max Act: 4.0065. Min Act: -0.1700
Data Index: 5210500 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3191. Min Range: -4.3191
Max Act: 4.0691. Min Act: -0.1700
Data Index: 2850564 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3191. Min Range: -4.3191
Max Act: 3.9753. Min Act: -0.1700
Data Index: 7350039 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3191. Min Range: -4.3191
Max Act: 4.0065. Min Act: -0.1700
Data Index: 6376304 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3191. Min Range: -4.3191
Max Act: 3.9440. Min Act: -0.1700
Data Index: 3219009 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3191. Min Range: -4.3191
Max Act: 4.0065. Min Act: -0.1700
Data Index: 769720 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3191. Min Range: -4.3191
Max Act: 3.9440. Min Act: -0.1700
Data Index: 8741334 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3191. Min Range: -4.3191
Max Act: 3.9440. Min Act: -0.1700
Data Index: 3230971 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3191. Min Range: -4.3191
Max Act: 3.9753. Min Act: -0.1698
Data Index: 6603872 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3191. Min Range: -4.3191
Max Act: 3.9440. Min Act: -0.1700
Data Index: 1759168 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3191. Min Range: -4.3191
Max Act: 3.8815. Min Act: -0.1700
Data Index: 399293 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19