Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3501 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.7623. Min Act: -0.1700
Data Index: 7218993 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.7623. Min Act: -0.1700
Data Index: 3811136 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.7623. Min Act: -0.1700
Data Index: 4648097 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.7292. Min Act: -0.1700
Data Index: 7218988 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.7540. Min Act: -0.1700
Data Index: 5844882 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.7128. Min Act: -0.1700
Data Index: 7218987 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.7046. Min Act: -0.1700
Data Index: 1230161 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.7046. Min Act: -0.1700
Data Index: 6766361 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.6883. Min Act: -0.1700
Data Index: 7219008 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.6883. Min Act: -0.1700
Data Index: 7218997 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.6560. Min Act: -0.1700
Data Index: 7219007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.6560. Min Act: -0.1700
Data Index: 529132 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.6399. Min Act: -0.1699
Data Index: 2633994 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.6480. Min Act: -0.1700
Data Index: 8786563 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.6399. Min Act: -0.1700
Data Index: 6980543 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.6320. Min Act: -0.1700
Data Index: 6499793 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.6161. Min Act: -0.1700
Data Index: 4993231 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.6240. Min Act: -0.1700
Data Index: 312635 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.6240. Min Act: -0.1700
Data Index: 8812512 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7623. Min Range: -0.7623
Max Act: 0.6161. Min Act: -0.1699
Data Index: 898362 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19