Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2031 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5249. Min Range: -7.5249
Max Act: 7.5249. Min Act: -0.1700
Data Index: 3381330 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5249. Min Range: -7.5249
Max Act: 7.4624. Min Act: -0.1700
Data Index: 2780305 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5249. Min Range: -7.5249
Max Act: 7.3061. Min Act: -0.1700
Data Index: 820210 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5249. Min Range: -7.5249
Max Act: 7.3061. Min Act: -0.1700
Data Index: 5751765 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5249. Min Range: -7.5249
Max Act: 7.2436. Min Act: -0.1700
Data Index: 4908815 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5249. Min Range: -7.5249
Max Act: 7.1499. Min Act: -0.1700
Data Index: 1208860 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5249. Min Range: -7.5249
Max Act: 7.1811. Min Act: -0.1700
Data Index: 4399256 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5249. Min Range: -7.5249
Max Act: 7.0874. Min Act: -0.1700
Data Index: 2634104 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5249. Min Range: -7.5249
Max Act: 7.0874. Min Act: -0.1700
Data Index: 1151709 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5249. Min Range: -7.5249
Max Act: 7.1186. Min Act: -0.1700
Data Index: 5222476 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5249. Min Range: -7.5249
Max Act: 7.0561. Min Act: -0.1700
Data Index: 7173173 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5249. Min Range: -7.5249
Max Act: 6.9936. Min Act: -0.1700
Data Index: 6399255 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5249. Min Range: -7.5249
Max Act: 6.9624. Min Act: -0.1700
Data Index: 6532485 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5249. Min Range: -7.5249
Max Act: 6.9936. Min Act: -0.1700
Data Index: 7173176 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5249. Min Range: -7.5249
Max Act: 6.9624. Min Act: -0.1700
Data Index: 3682965 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5249. Min Range: -7.5249
Max Act: 6.9624. Min Act: -0.1700
Data Index: 8050314 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5249. Min Range: -7.5249
Max Act: 6.9624. Min Act: -0.1700
Data Index: 7943849 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5249. Min Range: -7.5249
Max Act: 6.9624. Min Act: -0.1700
Data Index: 1783451 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5249. Min Range: -7.5249
Max Act: 6.9624. Min Act: -0.1700
Data Index: 3617534 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5249. Min Range: -7.5249
Max Act: 6.8999. Min Act: -0.1700
Data Index: 5050452 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19