Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4803 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2153. Min Range: -6.2153
Max Act: 6.2153. Min Act: -0.1700
Data Index: 4107488 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2153. Min Range: -6.2153
Max Act: 6.1528. Min Act: -0.1700
Data Index: 283747 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.9966. Min Act: -0.1700
Data Index: 7748769 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.9653. Min Act: -0.1700
Data Index: 3004973 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.9653. Min Act: -0.1700
Data Index: 4211192 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.9341. Min Act: -0.1700
Data Index: 7781186 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.8716. Min Act: -0.1700
Data Index: 4293061 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.8716. Min Act: -0.1700
Data Index: 4309400 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.8716. Min Act: -0.1700
Data Index: 2244441 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.8716. Min Act: -0.1700
Data Index: 527553 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.8091. Min Act: -0.1700
Data Index: 8025084 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.8091. Min Act: -0.1700
Data Index: 931075 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.7778. Min Act: -0.1700
Data Index: 2306189 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.7778. Min Act: -0.1700
Data Index: 1797924 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.7778. Min Act: -0.1700
Data Index: 1822657 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.7466. Min Act: -0.1700
Data Index: 8336328 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.7466. Min Act: -0.1700
Data Index: 8136986 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.7466. Min Act: -0.1700
Data Index: 880287 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.7466. Min Act: -0.1700
Data Index: 392528 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2153. Min Range: -6.2153
Max Act: 5.7153. Min Act: -0.1700
Data Index: 6705805 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19