Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.8164. Min Act: -0.1700
Data Index: 4637723 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.6914. Min Act: -0.1700
Data Index: 7471390 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.6914. Min Act: -0.1700
Data Index: 7221171 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.6289. Min Act: -0.1700
Data Index: 5904010 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.5664. Min Act: -0.1700
Data Index: 5848280 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.3789. Min Act: -0.1700
Data Index: 8204719 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.3789. Min Act: -0.1700
Data Index: 5920282 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.4414. Min Act: -0.1700
Data Index: 8040396 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.3164. Min Act: -0.1700
Data Index: 243417 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.3164. Min Act: -0.1700
Data Index: 6380836 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.2852. Min Act: -0.1700
Data Index: 5359906 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.2539. Min Act: -0.1700
Data Index: 8512422 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.2227. Min Act: -0.1700
Data Index: 6792746 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.2539. Min Act: -0.1700
Data Index: 2958433 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.2227. Min Act: -0.1700
Data Index: 2411418 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.2227. Min Act: -0.1700
Data Index: 5270609 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.1914. Min Act: -0.1700
Data Index: 7064435 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.1914. Min Act: -0.1700
Data Index: 3547421 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.1602. Min Act: -0.1700
Data Index: 1730180 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8164. Min Range: -7.8164
Max Act: 7.1289. Min Act: -0.1700
Data Index: 4029702 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19