Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3025 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3981. Min Range: -6.3981
Max Act: 6.3981. Min Act: -0.1700
Data Index: 8182088 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3981. Min Range: -6.3981
Max Act: 6.3669. Min Act: -0.1700
Data Index: 1840426 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3981. Min Range: -6.3981
Max Act: 6.3669. Min Act: -0.1700
Data Index: 6254690 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3981. Min Range: -6.3981
Max Act: 6.0544. Min Act: -0.1700
Data Index: 4068059 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.9919. Min Act: -0.1700
Data Index: 7148537 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.9294. Min Act: -0.1700
Data Index: 6115060 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.9919. Min Act: -0.1700
Data Index: 5094781 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.9294. Min Act: -0.1700
Data Index: 7457996 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.9294. Min Act: -0.1700
Data Index: 7928672 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.8981. Min Act: -0.1700
Data Index: 6318273 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.8044. Min Act: -0.1700
Data Index: 427728 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.8044. Min Act: -0.1700
Data Index: 5747836 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.8044. Min Act: -0.1700
Data Index: 3217983 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.8044. Min Act: -0.1700
Data Index: 7503426 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.8044. Min Act: -0.1700
Data Index: 5936510 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.7731. Min Act: -0.1700
Data Index: 8450004 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.7731. Min Act: -0.1700
Data Index: 8294831 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.7731. Min Act: -0.1700
Data Index: 996469 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.7419. Min Act: -0.1700
Data Index: 743901 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.7419. Min Act: -0.1700
Data Index: 1985899 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19