Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5359 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.6746. Min Act: -0.1700
Data Index: 4717903 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.6121. Min Act: -0.1700
Data Index: 4296950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5809. Min Act: -0.1700
Data Index: 7364504 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5809. Min Act: -0.1700
Data Index: 480455 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5809. Min Act: -0.1700
Data Index: 5866055 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5809. Min Act: -0.1700
Data Index: 3920608 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5809. Min Act: -0.1700
Data Index: 2896616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5496. Min Act: -0.1700
Data Index: 3355394 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5496. Min Act: -0.1700
Data Index: 17731 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5496. Min Act: -0.1700
Data Index: 3312497 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5496. Min Act: -0.1700
Data Index: 6696700 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5496. Min Act: -0.1700
Data Index: 1515397 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5496. Min Act: -0.1700
Data Index: 8594138 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5496. Min Act: -0.1700
Data Index: 7577317 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5496. Min Act: -0.1700
Data Index: 160977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5184. Min Act: -0.1700
Data Index: 3231667 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5184. Min Act: -0.1700
Data Index: 6283224 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5184. Min Act: -0.1700
Data Index: 3287645 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5184. Min Act: -0.1700
Data Index: 1402332 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6746. Min Range: -4.6746
Max Act: 4.5184. Min Act: -0.1700
Data Index: 5125114 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19