Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5926 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.2993. Min Act: -0.1700
Data Index: 1162731 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.2681. Min Act: -0.1700
Data Index: 8259942 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.2368. Min Act: -0.1700
Data Index: 8060507 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1743. Min Act: -0.1700
Data Index: 4391236 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1743. Min Act: -0.1700
Data Index: 1020847 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1743. Min Act: -0.1700
Data Index: 435113 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1743. Min Act: -0.1700
Data Index: 7482033 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1743. Min Act: -0.1700
Data Index: 748577 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1431. Min Act: -0.1700
Data Index: 7489325 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1431. Min Act: -0.1700
Data Index: 5366833 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1431. Min Act: -0.1700
Data Index: 1543739 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1431. Min Act: -0.1700
Data Index: 3965360 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1431. Min Act: -0.1700
Data Index: 1288945 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1431. Min Act: -0.1700
Data Index: 307917 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1431. Min Act: -0.1700
Data Index: 4529748 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1118. Min Act: -0.1700
Data Index: 757485 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1118. Min Act: -0.1700
Data Index: 7514451 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1118. Min Act: -0.1700
Data Index: 7740239 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1118. Min Act: -0.1700
Data Index: 6734539 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2993. Min Range: -4.2993
Max Act: 4.1118. Min Act: -0.1700
Data Index: 8175151 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19