Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4566 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7776. Min Range: -6.7776
Max Act: 6.7776. Min Act: -0.1700
Data Index: 103924 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7776. Min Range: -6.7776
Max Act: 6.4651. Min Act: -0.1700
Data Index: 7956334 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7776. Min Range: -6.7776
Max Act: 6.4339. Min Act: -0.1700
Data Index: 4892261 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7776. Min Range: -6.7776
Max Act: 6.3089. Min Act: -0.1700
Data Index: 2358415 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7776. Min Range: -6.7776
Max Act: 6.3089. Min Act: -0.1700
Data Index: 7945954 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7776. Min Range: -6.7776
Max Act: 6.3089. Min Act: -0.1700
Data Index: 8091614 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7776. Min Range: -6.7776
Max Act: 6.2776. Min Act: -0.1700
Data Index: 305198 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7776. Min Range: -6.7776
Max Act: 6.2151. Min Act: -0.1700
Data Index: 8714426 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7776. Min Range: -6.7776
Max Act: 6.1839. Min Act: -0.1700
Data Index: 5017713 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7776. Min Range: -6.7776
Max Act: 6.1526. Min Act: -0.1700
Data Index: 1278219 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7776. Min Range: -6.7776
Max Act: 6.1214. Min Act: -0.1700
Data Index: 6627075 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7776. Min Range: -6.7776
Max Act: 6.1214. Min Act: -0.1700
Data Index: 1684478 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7776. Min Range: -6.7776
Max Act: 6.0901. Min Act: -0.1700
Data Index: 275334 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7776. Min Range: -6.7776
Max Act: 5.9651. Min Act: -0.1700
Data Index: 6867086 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7776. Min Range: -6.7776
Max Act: 6.0276. Min Act: -0.1700
Data Index: 1414778 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7776. Min Range: -6.7776
Max Act: 5.9964. Min Act: -0.1700
Data Index: 6653903 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7776. Min Range: -6.7776
Max Act: 5.9651. Min Act: -0.1700
Data Index: 4487379 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7776. Min Range: -6.7776
Max Act: 5.9339. Min Act: -0.1700
Data Index: 8023136 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7776. Min Range: -6.7776
Max Act: 5.9026. Min Act: -0.1700
Data Index: 1276869 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7776. Min Range: -6.7776
Max Act: 5.9026. Min Act: -0.1700
Data Index: 5182324 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19