Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3079 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0603. Min Range: -7.0603
Max Act: 7.0603. Min Act: -0.1700
Data Index: 302459 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.8416. Min Act: -0.1700
Data Index: 1291607 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.6853. Min Act: -0.1700
Data Index: 6585239 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.4666. Min Act: -0.1700
Data Index: 6871046 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.4353. Min Act: -0.1700
Data Index: 1167301 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.4353. Min Act: -0.1700
Data Index: 4846571 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.4666. Min Act: -0.1700
Data Index: 7406520 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.4041. Min Act: -0.1700
Data Index: 1337649 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.4041. Min Act: -0.1700
Data Index: 8470884 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.4041. Min Act: -0.1700
Data Index: 4051530 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.3728. Min Act: -0.1700
Data Index: 6268366 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.3728. Min Act: -0.1700
Data Index: 7761095 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.3728. Min Act: -0.1700
Data Index: 5353114 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.3416. Min Act: -0.1700
Data Index: 7684889 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.3416. Min Act: -0.1700
Data Index: 1368905 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.3103. Min Act: -0.1700
Data Index: 1413572 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.3103. Min Act: -0.1700
Data Index: 7444368 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.3103. Min Act: -0.1700
Data Index: 2497369 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.3416. Min Act: -0.1700
Data Index: 7493718 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0603. Min Range: -7.0603
Max Act: 6.2791. Min Act: -0.1700
Data Index: 2224851 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19