Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3837 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0751. Min Range: -8.0751
Max Act: 8.0751. Min Act: -0.1700
Data Index: 2641013 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.9189. Min Act: -0.1700
Data Index: 4341541 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.7314. Min Act: -0.1700
Data Index: 3506367 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.6689. Min Act: -0.1700
Data Index: 6146999 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.7001. Min Act: -0.1700
Data Index: 2915735 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.6689. Min Act: -0.1700
Data Index: 7167671 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.6376. Min Act: -0.1700
Data Index: 2674827 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.6376. Min Act: -0.1700
Data Index: 73602 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.6064. Min Act: -0.1700
Data Index: 4612679 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.6064. Min Act: -0.1700
Data Index: 6140430 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.6064. Min Act: -0.1700
Data Index: 2675748 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.5439. Min Act: -0.1700
Data Index: 5150972 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.5126. Min Act: -0.1700
Data Index: 5381010 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.4501. Min Act: -0.1700
Data Index: 4831386 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.4189. Min Act: -0.1700
Data Index: 3110968 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.4189. Min Act: -0.1700
Data Index: 5561839 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.4501. Min Act: -0.1700
Data Index: 3866499 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.4189. Min Act: -0.1700
Data Index: 3647624 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.3876. Min Act: -0.1700
Data Index: 8758869 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0751. Min Range: -8.0751
Max Act: 7.4189. Min Act: -0.1700
Data Index: 1720703 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19