Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 90 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.5421. Min Act: -0.1700
Data Index: 1483547 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.3859. Min Act: -0.1700
Data Index: 8600305 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.2921. Min Act: -0.1700
Data Index: 6278493 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.2609. Min Act: -0.1700
Data Index: 1936629 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.2296. Min Act: -0.1700
Data Index: 7434356 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.1671. Min Act: -0.1700
Data Index: 8199599 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.1046. Min Act: -0.1700
Data Index: 2042317 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.1046. Min Act: -0.1700
Data Index: 165858 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.1046. Min Act: -0.1700
Data Index: 8353971 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.1046. Min Act: -0.1700
Data Index: 2272813 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.0734. Min Act: -0.1700
Data Index: 3060634 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.0734. Min Act: -0.1699
Data Index: 2601259 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.0734. Min Act: -0.1700
Data Index: 5843412 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.0734. Min Act: -0.1698
Data Index: 1463718 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.1046. Min Act: -0.1700
Data Index: 154924 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.0421. Min Act: -0.1700
Data Index: 5117609 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.0421. Min Act: -0.1700
Data Index: 4196767 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.0421. Min Act: -0.1700
Data Index: 2493247 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.0421. Min Act: -0.1700
Data Index: 4914593 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5421. Min Range: -5.5421
Max Act: 5.0421. Min Act: -0.1700
Data Index: 4535523 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19