Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3254 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2589. Min Range: -7.2589
Max Act: 7.2589. Min Act: -0.1700
Data Index: 8529395 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2589. Min Range: -7.2589
Max Act: 7.0714. Min Act: -0.1700
Data Index: 8705860 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.9777. Min Act: -0.1700
Data Index: 8090507 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.8839. Min Act: -0.1700
Data Index: 823578 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.8527. Min Act: -0.1700
Data Index: 6470511 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.8214. Min Act: -0.1700
Data Index: 7176008 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.8214. Min Act: -0.1700
Data Index: 4349315 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.7589. Min Act: -0.1700
Data Index: 1869134 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.7902. Min Act: -0.1700
Data Index: 7831008 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.7589. Min Act: -0.1700
Data Index: 4260034 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.7589. Min Act: -0.1700
Data Index: 8711993 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.7277. Min Act: -0.1700
Data Index: 905482 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.7277. Min Act: -0.1700
Data Index: 2184793 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.6652. Min Act: -0.1700
Data Index: 1274978 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.6027. Min Act: -0.1700
Data Index: 2779892 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.5402. Min Act: -0.1700
Data Index: 6158324 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.4777. Min Act: -0.1700
Data Index: 1831561 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.4777. Min Act: -0.1700
Data Index: 7644444 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.4152. Min Act: -0.1700
Data Index: 2302334 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2589. Min Range: -7.2589
Max Act: 6.4152. Min Act: -0.1700
Data Index: 3420486 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19