Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.7361. Min Act: -0.1700
Data Index: 712534 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.6736. Min Act: -0.1700
Data Index: 1336647 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.4549. Min Act: -0.1700
Data Index: 7506136 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.3924. Min Act: -0.1700
Data Index: 8427540 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.3611. Min Act: -0.1700
Data Index: 2250334 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.2986. Min Act: -0.1700
Data Index: 4735271 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.2986. Min Act: -0.1700
Data Index: 3964295 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.2986. Min Act: -0.1700
Data Index: 8456644 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.2674. Min Act: -0.1700
Data Index: 7238628 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.2361. Min Act: -0.1700
Data Index: 672895 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.2361. Min Act: -0.1700
Data Index: 644115 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.2049. Min Act: -0.1700
Data Index: 1979182 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.1736. Min Act: -0.1700
Data Index: 2007965 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.1424. Min Act: -0.1700
Data Index: 6989109 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.1424. Min Act: -0.1700
Data Index: 5362425 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.1736. Min Act: -0.1700
Data Index: 7174820 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.1424. Min Act: -0.1700
Data Index: 4738918 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.1424. Min Act: -0.1700
Data Index: 1716237 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.1424. Min Act: -0.1700
Data Index: 3441350 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.1111. Min Act: -0.1700
Data Index: 4639278 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19