Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5136. Min Range: -7.5136
Max Act: 7.5136. Min Act: -0.1700
Data Index: 7168710 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5136. Min Range: -7.5136
Max Act: 7.4198. Min Act: -0.1700
Data Index: 5895507 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5136. Min Range: -7.5136
Max Act: 7.2948. Min Act: -0.1700
Data Index: 6701822 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5136. Min Range: -7.5136
Max Act: 7.2948. Min Act: -0.1700
Data Index: 1325496 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5136. Min Range: -7.5136
Max Act: 7.2636. Min Act: -0.1700
Data Index: 5744102 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5136. Min Range: -7.5136
Max Act: 7.2011. Min Act: -0.1700
Data Index: 4739518 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5136. Min Range: -7.5136
Max Act: 7.0761. Min Act: -0.1700
Data Index: 1370797 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5136. Min Range: -7.5136
Max Act: 7.0136. Min Act: -0.1700
Data Index: 5666093 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5136. Min Range: -7.5136
Max Act: 7.0448. Min Act: -0.1700
Data Index: 781005 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5136. Min Range: -7.5136
Max Act: 7.0448. Min Act: -0.1700
Data Index: 1406197 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5136. Min Range: -7.5136
Max Act: 7.0136. Min Act: -0.1700
Data Index: 571209 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5136. Min Range: -7.5136
Max Act: 7.0136. Min Act: -0.1700
Data Index: 8695594 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5136. Min Range: -7.5136
Max Act: 7.0136. Min Act: -0.1700
Data Index: 495169 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5136. Min Range: -7.5136
Max Act: 6.9823. Min Act: -0.1700
Data Index: 7187334 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5136. Min Range: -7.5136
Max Act: 6.9511. Min Act: -0.1700
Data Index: 1188591 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5136. Min Range: -7.5136
Max Act: 6.9511. Min Act: -0.1700
Data Index: 7940986 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5136. Min Range: -7.5136
Max Act: 6.8886. Min Act: -0.1700
Data Index: 5581737 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5136. Min Range: -7.5136
Max Act: 6.9198. Min Act: -0.1700
Data Index: 7592278 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5136. Min Range: -7.5136
Max Act: 6.8886. Min Act: -0.1700
Data Index: 908454 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5136. Min Range: -7.5136
Max Act: 6.8886. Min Act: -0.1700
Data Index: 4305516 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19