Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 482 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.5547. Min Act: -0.1700
Data Index: 1449273 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.5234. Min Act: -0.1700
Data Index: 4358687 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.5234. Min Act: -0.1700
Data Index: 288867 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.5234. Min Act: -0.1700
Data Index: 5492087 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.5234. Min Act: -0.1700
Data Index: 7927662 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.5234. Min Act: -0.1700
Data Index: 534587 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.4922. Min Act: -0.1700
Data Index: 2734757 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.4922. Min Act: -0.1700
Data Index: 4460764 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.4609. Min Act: -0.1700
Data Index: 2275173 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.4609. Min Act: -0.1700
Data Index: 1384466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.4609. Min Act: -0.1700
Data Index: 5096608 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.4609. Min Act: -0.1700
Data Index: 5093829 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.4609. Min Act: -0.1700
Data Index: 66856 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.4609. Min Act: -0.1700
Data Index: 4481130 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.4297. Min Act: -0.1700
Data Index: 5796623 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.4297. Min Act: -0.1700
Data Index: 1122458 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.4297. Min Act: -0.1700
Data Index: 1197159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.4297. Min Act: -0.1700
Data Index: 5821308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.4297. Min Act: -0.1700
Data Index: 41826 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5547. Min Range: -5.5547
Max Act: 5.4297. Min Act: -0.1700
Data Index: 6319570 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19