Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4870 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3016. Min Range: -7.3016
Max Act: 7.3016. Min Act: -0.1700
Data Index: 7378859 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.8016. Min Act: -0.1700
Data Index: 2410276 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.6453. Min Act: -0.1700
Data Index: 7378863 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.6141. Min Act: -0.1700
Data Index: 8461810 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.5828. Min Act: -0.1700
Data Index: 2188506 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.5203. Min Act: -0.1700
Data Index: 2550052 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.5516. Min Act: -0.1700
Data Index: 7378861 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.4578. Min Act: -0.1700
Data Index: 958722 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.3641. Min Act: -0.1700
Data Index: 7378857 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.3641. Min Act: -0.1700
Data Index: 3333472 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.3328. Min Act: -0.1700
Data Index: 9609 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.3328. Min Act: -0.1700
Data Index: 6014355 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.3016. Min Act: -0.1700
Data Index: 2410296 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.3016. Min Act: -0.1700
Data Index: 7378860 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.2703. Min Act: -0.1700
Data Index: 2188514 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.2703. Min Act: -0.1700
Data Index: 2410280 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.1766. Min Act: -0.1700
Data Index: 7378868 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.1453. Min Act: -0.1700
Data Index: 7378856 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.1453. Min Act: -0.1700
Data Index: 7378869 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3016. Min Range: -7.3016
Max Act: 6.1453. Min Act: -0.1700
Data Index: 2130708 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19