Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3763 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.4827. Min Act: -0.1700
Data Index: 7332224 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.2640. Min Act: -0.1700
Data Index: 4477369 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.2015. Min Act: -0.1700
Data Index: 340828 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.2327. Min Act: -0.1700
Data Index: 1484049 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.2015. Min Act: -0.1700
Data Index: 1587790 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.1702. Min Act: -0.1700
Data Index: 583555 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.1390. Min Act: -0.1700
Data Index: 3735484 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.1390. Min Act: -0.1700
Data Index: 1545161 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.1702. Min Act: -0.1700
Data Index: 875158 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.0765. Min Act: -0.1700
Data Index: 6221953 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.1077. Min Act: -0.1700
Data Index: 7332229 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.0765. Min Act: -0.1700
Data Index: 8504844 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.0452. Min Act: -0.1700
Data Index: 7231860 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.0452. Min Act: -0.1700
Data Index: 8376621 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.0452. Min Act: -0.1700
Data Index: 875997 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.0140. Min Act: -0.1700
Data Index: 1587786 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.0765. Min Act: -0.1700
Data Index: 4660470 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.0452. Min Act: -0.1700
Data Index: 4127857 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4827. Min Range: -5.4827
Max Act: 5.0140. Min Act: -0.1700
Data Index: 3791007 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4827. Min Range: -5.4827
Max Act: 4.9515. Min Act: -0.1700
Data Index: 1587761 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19