Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 583 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.6621. Min Act: -0.1700
Data Index: 1532266 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.3495. Min Act: -0.1700
Data Index: 2511813 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.2870. Min Act: -0.1700
Data Index: 2532976 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.2558. Min Act: -0.1700
Data Index: 1033270 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.2558. Min Act: -0.1700
Data Index: 2445805 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.2245. Min Act: -0.1700
Data Index: 2459228 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.2245. Min Act: -0.1700
Data Index: 4027900 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.1933. Min Act: -0.1700
Data Index: 8496272 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.1620. Min Act: -0.1700
Data Index: 4769283 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.1308. Min Act: -0.1700
Data Index: 7934433 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.1308. Min Act: -0.1700
Data Index: 2456615 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.1308. Min Act: -0.1700
Data Index: 8050632 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.1308. Min Act: -0.1700
Data Index: 4198503 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.0995. Min Act: -0.1700
Data Index: 2628572 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.0995. Min Act: -0.1700
Data Index: 6414925 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.0683. Min Act: -0.1700
Data Index: 7325840 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.0370. Min Act: -0.1700
Data Index: 3644486 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.0683. Min Act: -0.1700
Data Index: 6195303 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.0683. Min Act: -0.1700
Data Index: 5975680 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6621. Min Range: -4.6621
Max Act: 4.0683. Min Act: -0.1700
Data Index: 2847874 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19