Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4490 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3456. Min Range: -11.3456
Max Act: 11.3456. Min Act: -0.1700
Data Index: 6500139 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3456. Min Range: -11.3456
Max Act: 11.2831. Min Act: -0.1700
Data Index: 8817894 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3456. Min Range: -11.3456
Max Act: 11.3456. Min Act: -0.1700
Data Index: 7993417 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3456. Min Range: -11.3456
Max Act: 11.2206. Min Act: -0.1700
Data Index: 4258611 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3456. Min Range: -11.3456
Max Act: 11.1581. Min Act: -0.1700
Data Index: 3399718 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3456. Min Range: -11.3456
Max Act: 11.0956. Min Act: -0.1700
Data Index: 2824345 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3456. Min Range: -11.3456
Max Act: 11.0956. Min Act: -0.1700
Data Index: 7100867 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3456. Min Range: -11.3456
Max Act: 10.9706. Min Act: -0.1700
Data Index: 6470242 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3456. Min Range: -11.3456
Max Act: 10.9706. Min Act: -0.1700
Data Index: 4052942 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3456. Min Range: -11.3456
Max Act: 11.0331. Min Act: -0.1700
Data Index: 7235624 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3456. Min Range: -11.3456
Max Act: 10.9706. Min Act: -0.1700
Data Index: 7235622 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3456. Min Range: -11.3456
Max Act: 10.9081. Min Act: -0.1700
Data Index: 1626736 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3456. Min Range: -11.3456
Max Act: 10.9081. Min Act: -0.1700
Data Index: 4584019 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3456. Min Range: -11.3456
Max Act: 10.9081. Min Act: -0.1700
Data Index: 3911160 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3456. Min Range: -11.3456
Max Act: 10.9081. Min Act: -0.1700
Data Index: 7657768 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3456. Min Range: -11.3456
Max Act: 10.9081. Min Act: -0.1700
Data Index: 1216106 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3456. Min Range: -11.3456
Max Act: 10.9081. Min Act: -0.1700
Data Index: 1660504 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3456. Min Range: -11.3456
Max Act: 10.8456. Min Act: -0.1700
Data Index: 789896 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3456. Min Range: -11.3456
Max Act: 10.8456. Min Act: -0.1700
Data Index: 7778803 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3456. Min Range: -11.3456
Max Act: 10.8456. Min Act: -0.1700
Data Index: 8354977 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19