Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6393 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4808. Min Range: -7.4808
Max Act: 7.4808. Min Act: -0.1700
Data Index: 3727933 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4808. Min Range: -7.4808
Max Act: 7.3245. Min Act: -0.1700
Data Index: 5612656 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4808. Min Range: -7.4808
Max Act: 7.2308. Min Act: -0.1700
Data Index: 7679719 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4808. Min Range: -7.4808
Max Act: 7.1683. Min Act: -0.1700
Data Index: 766363 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4808. Min Range: -7.4808
Max Act: 7.1683. Min Act: -0.1700
Data Index: 3804011 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4808. Min Range: -7.4808
Max Act: 7.1370. Min Act: -0.1700
Data Index: 326183 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4808. Min Range: -7.4808
Max Act: 7.1058. Min Act: -0.1700
Data Index: 3041531 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4808. Min Range: -7.4808
Max Act: 7.0745. Min Act: -0.1700
Data Index: 8675134 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4808. Min Range: -7.4808
Max Act: 7.1058. Min Act: -0.1700
Data Index: 2456163 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4808. Min Range: -7.4808
Max Act: 7.0745. Min Act: -0.1700
Data Index: 2054521 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4808. Min Range: -7.4808
Max Act: 7.0433. Min Act: -0.1700
Data Index: 3334661 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4808. Min Range: -7.4808
Max Act: 6.9808. Min Act: -0.1700
Data Index: 4566885 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4808. Min Range: -7.4808
Max Act: 7.0120. Min Act: -0.1700
Data Index: 3309692 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4808. Min Range: -7.4808
Max Act: 7.0120. Min Act: -0.1700
Data Index: 1821571 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4808. Min Range: -7.4808
Max Act: 6.9808. Min Act: -0.1700
Data Index: 3071732 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4808. Min Range: -7.4808
Max Act: 6.9808. Min Act: -0.1700
Data Index: 6742622 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4808. Min Range: -7.4808
Max Act: 6.9495. Min Act: -0.1700
Data Index: 2097312 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4808. Min Range: -7.4808
Max Act: 6.9495. Min Act: -0.1700
Data Index: 2219323 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4808. Min Range: -7.4808
Max Act: 6.9495. Min Act: -0.1700
Data Index: 3388630 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4808. Min Range: -7.4808
Max Act: 6.9495. Min Act: -0.1700
Data Index: 6875949 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19