Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1231 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.7872. Min Act: -0.1700
Data Index: 151379 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.5060. Min Act: -0.1700
Data Index: 960137 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.5372. Min Act: -0.1700
Data Index: 194528 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.5060. Min Act: -0.1700
Data Index: 5524120 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.5372. Min Act: -0.1700
Data Index: 6706541 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.5372. Min Act: -0.1700
Data Index: 4489815 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.4122. Min Act: -0.1700
Data Index: 6550188 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.4435. Min Act: -0.1700
Data Index: 3335941 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.4435. Min Act: -0.1700
Data Index: 638160 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.3810. Min Act: -0.1700
Data Index: 489975 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.4435. Min Act: -0.1700
Data Index: 1401298 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.3810. Min Act: -0.1700
Data Index: 387759 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.4435. Min Act: -0.1700
Data Index: 7169736 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.4122. Min Act: -0.1700
Data Index: 2294797 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.3810. Min Act: -0.1700
Data Index: 1397273 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.3497. Min Act: -0.1700
Data Index: 667022 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.3810. Min Act: -0.1700
Data Index: 78137 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.3497. Min Act: -0.1700
Data Index: 1231438 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.3497. Min Act: -0.1700
Data Index: 4185567 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.3810. Min Act: -0.1700
Data Index: 6847618 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19