Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4340 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0659. Min Range: -7.0659
Max Act: 7.0659. Min Act: -0.1700
Data Index: 14432 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0659. Min Range: -7.0659
Max Act: 7.0346. Min Act: -0.1700
Data Index: 4653575 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.9409. Min Act: -0.1700
Data Index: 3182572 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.8159. Min Act: -0.1700
Data Index: 1584062 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.7221. Min Act: -0.1700
Data Index: 2874886 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.6909. Min Act: -0.1700
Data Index: 7972271 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.7221. Min Act: -0.1700
Data Index: 167935 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.5034. Min Act: -0.1700
Data Index: 6681559 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.5034. Min Act: -0.1700
Data Index: 6491701 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.4721. Min Act: -0.1700
Data Index: 7387239 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.4721. Min Act: -0.1700
Data Index: 2829585 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.4409. Min Act: -0.1700
Data Index: 6216014 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.4096. Min Act: -0.1700
Data Index: 7835733 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.3471. Min Act: -0.1700
Data Index: 3085162 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.3784. Min Act: -0.1700
Data Index: 1537824 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.3159. Min Act: -0.1700
Data Index: 3868123 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.3159. Min Act: -0.1700
Data Index: 7067257 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.3159. Min Act: -0.1700
Data Index: 1645382 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.2846. Min Act: -0.1700
Data Index: 4717957 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0659. Min Range: -7.0659
Max Act: 6.2846. Min Act: -0.1700
Data Index: 67090 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19