Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5370 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2165. Min Range: -5.2165
Max Act: 5.2165. Min Act: -0.1700
Data Index: 392824 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2165. Min Range: -5.2165
Max Act: 5.1540. Min Act: -0.1700
Data Index: 1036139 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.9353. Min Act: -0.1700
Data Index: 4364253 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.9665. Min Act: -0.1700
Data Index: 7741334 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.9353. Min Act: -0.1700
Data Index: 3803881 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.9040. Min Act: -0.1700
Data Index: 4906320 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.8728. Min Act: -0.1700
Data Index: 3668495 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.8728. Min Act: -0.1700
Data Index: 2143280 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.8415. Min Act: -0.1700
Data Index: 8248567 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.8415. Min Act: -0.1700
Data Index: 4272128 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.8103. Min Act: -0.1700
Data Index: 527396 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.8103. Min Act: -0.1700
Data Index: 3448313 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.8103. Min Act: -0.1700
Data Index: 5958780 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.8103. Min Act: -0.1700
Data Index: 248003 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.7790. Min Act: -0.1700
Data Index: 8152930 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.7790. Min Act: -0.1700
Data Index: 4641551 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.7790. Min Act: -0.1700
Data Index: 1050801 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.7790. Min Act: -0.1700
Data Index: 732919 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.7478. Min Act: -0.1700
Data Index: 6080421 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2165. Min Range: -5.2165
Max Act: 4.7478. Min Act: -0.1700
Data Index: 7524606 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19