Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2912 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0641. Min Range: -5.0641
Max Act: 5.0641. Min Act: -0.1700
Data Index: 1679106 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.8766. Min Act: -0.1700
Data Index: 3028949 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.7516. Min Act: -0.1700
Data Index: 8642230 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.7204. Min Act: -0.1700
Data Index: 8820015 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.6891. Min Act: -0.1700
Data Index: 7415622 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.6266. Min Act: -0.1700
Data Index: 2611845 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.6266. Min Act: -0.1700
Data Index: 3171334 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.6266. Min Act: -0.1700
Data Index: 5030282 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.5641. Min Act: -0.1700
Data Index: 3907088 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.5641. Min Act: -0.1700
Data Index: 6650083 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.5641. Min Act: -0.1700
Data Index: 8605617 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.5329. Min Act: -0.1700
Data Index: 6586781 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.5329. Min Act: -0.1700
Data Index: 3373275 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.5329. Min Act: -0.1700
Data Index: 5804773 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.5329. Min Act: -0.1700
Data Index: 3066773 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.5016. Min Act: -0.1700
Data Index: 6880210 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.5016. Min Act: -0.1700
Data Index: 4757429 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.5016. Min Act: -0.1700
Data Index: 3684748 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.5329. Min Act: -0.1700
Data Index: 8588188 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0641. Min Range: -5.0641
Max Act: 4.4704. Min Act: -0.1700
Data Index: 1374291 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19