Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0173. Min Range: -7.0173
Max Act: 7.0173. Min Act: -0.1700
Data Index: 6697734 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.8923. Min Act: -0.1700
Data Index: 5163989 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.6423. Min Act: -0.1700
Data Index: 5667404 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.6111. Min Act: -0.1700
Data Index: 4035437 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.6111. Min Act: -0.1700
Data Index: 1124514 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.5798. Min Act: -0.1700
Data Index: 7786577 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.5798. Min Act: -0.1700
Data Index: 7942670 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.5486. Min Act: -0.1700
Data Index: 8569728 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.5486. Min Act: -0.1700
Data Index: 428037 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.5486. Min Act: -0.1700
Data Index: 3629086 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.5173. Min Act: -0.1700
Data Index: 1155868 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.4548. Min Act: -0.1700
Data Index: 3687192 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.4548. Min Act: -0.1700
Data Index: 447464 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.3923. Min Act: -0.1700
Data Index: 3042016 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.4236. Min Act: -0.1700
Data Index: 4917373 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.4236. Min Act: -0.1700
Data Index: 7451583 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.4236. Min Act: -0.1700
Data Index: 2858797 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.3923. Min Act: -0.1700
Data Index: 5711638 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.3298. Min Act: -0.1700
Data Index: 2084605 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0173. Min Range: -7.0173
Max Act: 6.3923. Min Act: -0.1700
Data Index: 6156001 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19