Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1938 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1653. Min Range: -8.1653
Max Act: 8.1653. Min Act: -0.1700
Data Index: 3037623 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1653. Min Range: -8.1653
Max Act: 8.1653. Min Act: -0.1700
Data Index: 6353843 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1653. Min Range: -8.1653
Max Act: 8.0403. Min Act: -0.1700
Data Index: 5893790 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1653. Min Range: -8.1653
Max Act: 8.1028. Min Act: -0.1700
Data Index: 5863584 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.9778. Min Act: -0.1700
Data Index: 7897129 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.9778. Min Act: -0.1700
Data Index: 5132019 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.9153. Min Act: -0.1700
Data Index: 4027240 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.7903. Min Act: -0.1700
Data Index: 7528845 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.7591. Min Act: -0.1700
Data Index: 2041730 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.7278. Min Act: -0.1700
Data Index: 2574000 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.6966. Min Act: -0.1700
Data Index: 4854016 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.6341. Min Act: -0.1700
Data Index: 2341961 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.6341. Min Act: -0.1700
Data Index: 6480956 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.6028. Min Act: -0.1700
Data Index: 2437453 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.5716. Min Act: -0.1700
Data Index: 2827075 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.5716. Min Act: -0.1700
Data Index: 7051824 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.5403. Min Act: -0.1700
Data Index: 2290582 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.5403. Min Act: -0.1700
Data Index: 5010549 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.4778. Min Act: -0.1700
Data Index: 7847044 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1653. Min Range: -8.1653
Max Act: 7.5091. Min Act: -0.1700
Data Index: 4533404 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19