Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2222 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.8512. Min Act: -0.1700
Data Index: 5338761 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.8512. Min Act: -0.1700
Data Index: 464632 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.8824. Min Act: -0.1700
Data Index: 7816293 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.8512. Min Act: -0.1700
Data Index: 953962 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.7887. Min Act: -0.1700
Data Index: 8798284 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.8199. Min Act: -0.1700
Data Index: 2006273 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.7887. Min Act: -0.1700
Data Index: 5045043 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.7887. Min Act: -0.1700
Data Index: 5468806 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.7574. Min Act: -0.1700
Data Index: 3065171 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.7262. Min Act: -0.1700
Data Index: 1965396 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.7262. Min Act: -0.1700
Data Index: 7610642 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.7262. Min Act: -0.1700
Data Index: 3667519 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.7262. Min Act: -0.1700
Data Index: 2171614 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.6949. Min Act: -0.1700
Data Index: 7653043 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.6949. Min Act: -0.1700
Data Index: 2525656 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.6949. Min Act: -0.1700
Data Index: 1736658 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.6949. Min Act: -0.1700
Data Index: 7816296 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.6949. Min Act: -0.1700
Data Index: 8301290 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.6949. Min Act: -0.1700
Data Index: 399279 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8824. Min Range: -5.8824
Max Act: 5.6949. Min Act: -0.1700
Data Index: 5014930 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19