Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 358 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.3495. Min Act: -0.1700
Data Index: 4176041 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.3183. Min Act: -0.1700
Data Index: 1346411 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.3183. Min Act: -0.1700
Data Index: 1834690 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.3183. Min Act: -0.1700
Data Index: 6131419 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.3183. Min Act: -0.1700
Data Index: 5712110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2558. Min Act: -0.1700
Data Index: 8291074 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2558. Min Act: -0.1700
Data Index: 416894 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2558. Min Act: -0.1700
Data Index: 6681768 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2558. Min Act: -0.1700
Data Index: 2484168 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2245. Min Act: -0.1700
Data Index: 5725218 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2558. Min Act: -0.1700
Data Index: 427470 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2558. Min Act: -0.1700
Data Index: 2516680 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2245. Min Act: -0.1700
Data Index: 2129678 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2245. Min Act: -0.1700
Data Index: 5847913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2245. Min Act: -0.1700
Data Index: 5461335 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2245. Min Act: -0.1700
Data Index: 6400551 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2245. Min Act: -0.1700
Data Index: 5180778 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2245. Min Act: -0.1700
Data Index: 6973529 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2245. Min Act: -0.1700
Data Index: 5127342 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2245. Min Act: -0.1700
Data Index: 7968807 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19