Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.8767. Min Act: -0.1700
Data Index: 7990765 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.8142. Min Act: -0.1700
Data Index: 5561793 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.7517. Min Act: -0.1700
Data Index: 498890 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.7205. Min Act: -0.1700
Data Index: 8568760 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.7205. Min Act: -0.1700
Data Index: 1527987 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.7205. Min Act: -0.1700
Data Index: 5771980 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.6580. Min Act: -0.1700
Data Index: 868579 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.6892. Min Act: -0.1700
Data Index: 343485 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.7205. Min Act: -0.1700
Data Index: 2242111 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.6892. Min Act: -0.1700
Data Index: 2138182 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.6580. Min Act: -0.1700
Data Index: 8069773 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.6892. Min Act: -0.1700
Data Index: 2231890 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.6580. Min Act: -0.1700
Data Index: 8461729 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.6580. Min Act: -0.1700
Data Index: 5097975 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.6267. Min Act: -0.1700
Data Index: 5892335 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.5955. Min Act: -0.1700
Data Index: 963781 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.6267. Min Act: -0.1700
Data Index: 322396 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.5955. Min Act: -0.1700
Data Index: 7141655 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.5955. Min Act: -0.1699
Data Index: 6678531 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8767. Min Range: -6.8767
Max Act: 6.5955. Min Act: -0.1700
Data Index: 7060729 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19